Physical AI Brief

Driving world models serve as a pivotal technology for autonomous driving by simulating environmental dynamics. However, existing approaches predominantly focus on future scene generation, often overlooking comprehensive 3D scene understanding. Conversely, while Large Language Models (LLMs) demonstrate impressive reasoning capabilities, they lack the capacity to predict future geometric evolution, creating a significant disparity between semantic interpretation and physical simulation. To bridge this gap, we propose HERMES++, a unified driving world model that integrates 3D scene understanding and future geometry prediction within a single framework. Our approach addresses the distinct requirements of these tasks through synergistic designs. First, a BEV representation consolidates multi-view spatial information into a structure compatible with LLMs. Second, we introduce LLM-enhanced world queries to facilitate knowledge transfer from the understanding branch. Third, a Current-to-Future Link is designed to bridge the temporal gap, conditioning geometric evolution on semantic context. Finally, to enforce structural integrity, we employ a Joint Geometric Optimization strategy that integrates explicit geometric constraints with implicit latent regularization to align internal representations with geometry-aware priors. Extensive evaluations on multiple benchmarks validate the effectiveness of our method. HERMES++ achieves strong performance, outperforming specialist approaches in both future point cloud prediction and 3D scene understanding tasks. The model and code will be publicly released at https://github.com/H-EmbodVis/HERMESV2.

Human-robot collaboration has been studied primarily in dyadic or sequential settings. However, real homes require multiadic collaboration, where multiple humans and robots share a workspace, acting concurrently on interleaved subtasks with tight spatial and temporal coupling. This regime remains underexplored because close-proximity interaction between humans, robots, and objects creates persistent occlusion and rapid state changes, making reliable real-time 3D tracking the central bottleneck. No existing platform provides the real-time, occlusion-robust, room-scale perception needed to make this regime experimentally tractable. We present OmniRobotHome, the first room-scale residential platform that unifies wide-area real-time 3D human and object perception with coordinated multi-robot actuation in a shared world frame. The system instruments a natural home environment with 48 hardware-synchronized RGB cameras for markerless, occlusion-robust tracking of multiple humans and objects, temporally aligned with two Franka arms that act on live scene state. Continuous capture within this consistent frame further supports long-horizon human behavior modeling from accumulated trajectories. The platform makes the multiadic collaboration regime experimentally tractable. We focus on two central problems: safety in shared human-robot environments and human-anticipatory robotic assistance, and show that real-time perception and accumulated behavior memory each yield measurable gains in both.

Reconstructing 3D scenes from sparse, unposed images remains challenging under real-world conditions with varying illumination and transient occlusions. Existing methods rely on scene-specific optimization using appearance embeddings or dynamic masks, which requires extensive per-scene training and fails under sparse views. Moreover, evaluations on limited scenes raise questions about generalization. We present GenWildSplat, a feed-forward framework for sparse-view outdoor reconstruction that requires no per-scene optimization. Given unposed internet images, GenWildSplat predicts depth, camera parameters, and 3D Gaussians in a canonical space using learned geometric priors. An appearance adapter modulates appearance for target lighting conditions, while semantic segmentation handles transient objects. Through curriculum learning on synthetic and real data, GenWildSplat generalizes across diverse illumination and occlusion patterns. Evaluations on PhotoTourism and MegaScenes benchmark demonstrate state-of-the-art feed-forward rendering quality, achieving real-time inference without test-time optimization

Vision-Language-Action (VLA) models have increasingly incorporated reasoning mechanisms for complex robotic manipulation. However, existing approaches share a critical limitation: whether employing explicit linguistic reasoning that suffers from latency and discretization, or utilizing more expressive continuous latent reasoning, they are predominantly confined to static imitation learning that limits adaptability and generalization. While online reinforcement learning (RL) has been introduced to VLAs to enable trial-and-error exploration, current methods exclusively optimize the vanilla action space, bypassing the underlying physical reasoning process. In this paper, we present \textbf{LaST-R1}, a unified VLA framework that integrates latent Chain-of-Thought (CoT) reasoning over physical dynamics prior to action execution, along with a tailored RL post-training paradigm. Specifically, we propose \textbf{Latent-to-Action Policy Optimization (LAPO)}, a novel RL algorithm that jointly optimizes the latent reasoning process and the action generation. By bridging reasoning and control, LAPO improves the representation of physical world modeling and enhances robustness in interactive environments. Furthermore, an \textbf{adaptive latent CoT mechanism} is introduced to allow the policy to dynamically adjust its reasoning horizon based on environment complexity. Extensive experiments show that LaST-R1 achieves a near-perfect 99.8\% average success rate on the LIBERO benchmark with only one-shot supervised warm-up, significantly improving convergence speed and performance over prior state-of-the-art methods. In real-world deployments, LAPO post-training yields up to a 44\% improvement over the initial warm-up policy across four complex tasks, including both single-arm and dual-arm settings. Finally, LaST-R1 demonstrates strong generalization across simulated and real-world environments.

We show that Fréchet Distance (FD), long considered impractical as a training objective, can in fact be effectively optimized in the representation space. Our idea is simple: decouple the population size for FD estimation (e.g., 50k) from the batch size for gradient computation (e.g., 1024). We term this approach FD-loss. Optimizing FD-loss reveals several surprising findings. First, post-training a base generator with FD-loss in different representation spaces consistently improves visual quality. Under the Inception feature space, a one-step generator achieves0.72 FID on ImageNet 256x256. Second, the same FD-loss repurposes multi-step generators into strong one-step generators without teacher distillation, adversarial training or per-sample targets. Third, FID can misrank visual quality: modern representations can yield better samples despite worse Inception FID. This motivates FDr$^k$, a multi-representation metric. We hope this work will encourage further exploration of distributional distances in diverse representation spaces as both training objectives and evaluation metrics for generative models.

Recent visual generation models have made major progress in photorealism, typography, instruction following, and interactive editing, yet they still struggle with spatial reasoning, persistent state, long-horizon consistency, and causal understanding. We argue that the field should move beyond appearance synthesis toward intelligent visual generation: plausible visuals grounded in structure, dynamics, domain knowledge, and causal relations. To frame this shift, we introduce a five-level taxonomy: Atomic Generation, Conditional Generation, In-Context Generation, Agentic Generation, and World-Modeling Generation, progressing from passive renderers to interactive, agentic, world-aware generators. We analyze key technical drivers, including flow matching, unified understanding-and-generation models, improved visual representations, post-training, reward modeling, data curation, synthetic data distillation, and sampling acceleration. We further show that current evaluations often overestimate progress by emphasizing perceptual quality while missing structural, temporal, and causal failures. By combining benchmark review, in-the-wild stress tests, and expert-constrained case studies, this roadmap offers a capability-centered lens for understanding, evaluating, and advancing the next generation of intelligent visual generation systems.

Multiferroic domain walls in functional oxides exhibit properties distinct from the bulk and are increasingly exploited as active elements in nanoelectronic and photonic devices. Deterministic control of domain populations has typically remained limited to local control, or removal with temperature. Here we demonstrate continuous, reversible manipulation of the ferroelastic domain structure in single-crystal LaAlO$_3$ using in-situ uniaxial strain. Combining atomic force microscopy, X-ray diffraction, and Raman spectroscopy with first-principles calculations we map the complete microscopic evolution of the twin domain population through the strain-driven transition from the rhombohedral $R\bar{3}c$ ground state toward the predicted orthorhombic $Fmmm$ phase. Applied strains below $0.5\%$ produce pronounced surface flattening and large-scale domain reorganisation, establishing uniaxial strain as a technically accessible control parameter for ferroelastic domain engineering. These results open a route to active, real-time programming of domain architectures in LaAlO$_3$-based heterostructures, with implications for strain-tunable superconducting interfaces, nanoscale phonon-polariton optics, and ultrafast lattice control.

Reinforcement learning (RL) has become essential to the post-training of large language models (LLMs) for reasoning, agentic capabilities and alignment. Successful RL relies on sufficient exploration of diverse actions by the model during training, which creates a potential failure mode: a model could strategically alter its exploration during training to influence the subsequent training outcome. In this paper we study this behavior, called exploration hacking. First, we create model organisms of selective RL resistance by fine-tuning LLMs to follow specific underperformance strategies; these models can successfully resist our RL-based capability elicitation in agentic biosecurity and AI R&D environments while maintaining performance on related tasks. We then use our model organisms to evaluate detection and mitigation strategies, including monitoring, weight noising, and SFT-based elicitation. Finally, we show that current frontier models can exhibit explicit reasoning about suppressing their exploration when provided with sufficient information about their training context, with higher rates when this information is acquired indirectly through the environment. Together, our results suggest exploration hacking is a possible failure mode of RL on sufficiently capable LLMs.

Realistic long-horizon productivity work is strongly conditioned on user-specific computer environments, where much of the work context is stored and organized through directory structures and content-rich artifacts. To scale synthetic data creation for such productivity scenarios, we introduce Synthetic Computers at Scale, a scalable methodology for creating such environments with realistic folder hierarchies and content-rich artifacts (e.g., documents, spreadsheets, and presentations). Conditioned on each synthetic computer, we run long-horizon simulations: one agent creates productivity objectives that are specific to the computer's user and require multiple professional deliverables and about a month of human work; another agent then acts as that user and keeps working across the computer -- for example, navigating the filesystem for grounding, coordinating with simulated collaborators, and producing professional artifacts -- until these objectives are completed. In preliminary experiments, we create 1,000 synthetic computers and run long-horizon simulations on them; each run requires over 8 hours of agent runtime and spans more than 2,000 turns on average. These simulations produce rich experiential learning signals, whose effectiveness is validated by significant improvements in agent performance on both in-domain and out-of-domain productivity evaluations. Given that personas are abundant at billion scale, this methodology can in principle scale to millions or even billions of synthetic user worlds with sufficient compute, enabling broader coverage of diverse professions, roles, contexts, environments, and productivity needs. We argue that scalable synthetic computer creation, together with at-scale simulations, is highly promising as a foundational substrate for agent self-improvement and agentic reinforcement learning in long-horizon productivity scenarios.

We introduce AEGIS, A holistic benchmark for Evaluating forensic analysis of AI-Generated academic ImageS. Compared to existing benchmarks, AEGIS features three key advances: (1) Domain-Specific Complexity: covering seven academic categories with 39 fine-grained subtypes, exposing intrinsic forensic difficulty, where even GPT-5.1 reaches 48.80% overall performance and expert models achieve only limited localization accuracy (IoU 30.09%); (2) Diverse Forgery Simulations: modeling four prevalent academic forgery strategies across 25 generative models, with 11 yielding average forensic accuracy below 50%, showing that forensics lag behind generative advances; and (3) Multi-Dimensional Forensic Evaluation: jointly assessing detection, reasoning, and localization, revealing complementary strengths between model families, with multimodal large language models (MLLMs) at 84.74% accuracy in textual artifact recognition and expert detectors peaking at 79.54% accuracy in binary authenticity detection. By evaluating 25 leading MLLMs, nine expert models, and one unified multimodal understanding and generation model, AEGIS serves as a diagnostic testbed exposing fundamental limitations in academic image forensics.

Modern video diffusion models excel at appearance synthesis but still struggle with physical consistency: objects drift, collisions lack realistic rebound, and material responses seldom match their underlying properties. We present PhyCo, a framework that introduces continuous, interpretable, and physically grounded control into video generation. Our approach integrates three key components: (i) a large-scale dataset of over 100K photorealistic simulation videos where friction, restitution, deformation, and force are systematically varied across diverse scenarios; (ii) physics-supervised fine-tuning of a pretrained diffusion model using a ControlNet conditioned on pixel-aligned physical property maps; and (iii) VLM-guided reward optimization, where a fine-tuned vision-language model evaluates generated videos with targeted physics queries and provides differentiable feedback. This combination enables a generative model to produce physically consistent and controllable outputs through variations in physical attributes-without any simulator or geometry reconstruction at inference. On the Physics-IQ benchmark, PhyCo significantly improves physical realism over strong baselines, and human studies confirm clearer and more faithful control over physical attributes. Our results demonstrate a scalable path toward physically consistent, controllable generative video models that generalize beyond synthetic training environments.

Topological features play an essential role in ensuring geometric plausibility and structural consistency in image analysis tasks such as segmentation and skeletonization. However, integrating topology-preserving learning based on simple points into deep learning tasks remains challenging, as existing simple point detection methods are confined to binary images and are non-differentiable, rendering them incompatible with gradient-based optimization in modern deep learning. Moreover, morphological and purely data-driven approaches often fail to guaranty topological consistency. To address these limitations, we propose a novel method that directly computes simple points on continuous-valued images, enabling differentiable topological inference. Building on this theory, we develop an efficient skeleton extraction algorithm that preserves topological structures in binary and continuous-valued images. Furthermore, we design a variational model that enforces topological constraints by preserving topologically non-removable (i.e., non-simple) points, which can be seamlessly integrated into any deep neural network segmentation with softmax or sigmoid outputs. Experimental results demonstrate that the proposed approach effectively improves topological integrity and structural accuracy across multiple benchmarks. The codes are available in https://github.com/levnsio/CSP.

We present FlexiTac, a low-cost, open-source, and scalable piezoresistive tactile sensing solution designed for robotic end-effectors. FlexiTac is a practical "plug-in" module consisting of (i) thin, flexible tactile sensor pads that provide dense tactile signals and (ii) a compact multi-channel readout board that streams synchronized measurements for real-time control and large-scale data collection. FlexiTac pads adopt a sealed three-layer laminate stack (FPC-Velostat-FPC) with electrode patterns directly integrated into flexible printed circuits, substantially improving fabrication throughput and repeatability while maintaining mechanical compliance for deployment on both rigid and soft grippers. The readout electronics use widely available, low-cost components and stream tactile signals to a host computer at 100 Hz via serial communication. Across multiple configurations, including fingertip pads and larger tactile mats, FlexiTac can be mounted on diverse platforms without major mechanical redesign. We further show that FlexiTac supports modern tactile learning pipelines, including 3D visuo-tactile fusion for contact-aware decision making, cross-embodiment skill transfer, and real-to-sim-to-real fine-tuning with GPU-parallel tactile simulation. Our project page is available at https://flexitac.github.io/.

LLM agents are expected to complete end-to-end units of work across software tools, business services, and local workspaces. Yet many agent benchmarks freeze a curated task set at release time and grade mainly the final response, making it difficult to evaluate agents against evolving workflow demand or verify whether a task was executed. We introduce Claw-Eval-Live, a live benchmark for workflow agents that separates a refreshable signal layer, updated across releases from public workflow-demand signals, from a reproducible, time-stamped release snapshot. Each release is constructed from public workflow-demand signals, with ClawHub Top-500 skills used in the current release, and materialized as controlled tasks with fixed fixtures, services, workspaces, and graders. For grading, Claw-Eval-Live records execution traces, audit logs, service state, and post-run workspace artifacts, using deterministic checks when evidence is sufficient and structured LLM judging only for semantic dimensions. The release contains 105 tasks spanning controlled business services and local workspace repair, and evaluates 13 frontier models under a shared public pass rule. Experiments reveal that reliable workflow automation remains far from solved: the leading model passes only 66.7% of tasks and no model reaches 70%. Failures are structured by task family and execution surface, with HR, management, and multi-system business workflows as persistent bottlenecks and local workspace repair comparatively easier but unsaturated. Leaderboard rank alone is insufficient because models with similar pass rates can diverge in overall completion, and task-level discrimination concentrates in a middle band of tasks. Claw-Eval-Live suggests that workflow-agent evaluation should be grounded twice, in fresh external demand and in verifiable agent action.

Autonomous agents act through sandboxed containers and microVMs whose state spans filesystems, processes, and runtime artifacts. Checkpoint and restore (C/R) of this state is needed for fault tolerance, spot execution, RL rollout branching, and safe rollback-yet existing approaches fall into two extremes: application-level recovery preserves chat history but misses OS-side effects, while full per-turn checkpointing is correct but too expensive under dense co-location. The root cause is an agent-OS semantic gap: agent frameworks see tool calls but not their OS effects; the OS sees state changes but lacks turn-level context to judge recovery relevance. This gap hides massive sparsity: over 75% of agent turns produce no recovery-relevant state, so most checkpoints are unnecessary. Crab (Checkpoint-and-Restore for Agent SandBoxes) is a transparent host-side runtime that bridges this gap without modifying agents or C/R backends. An eBPF-based inspector classifies each turn's OS-visible effects to decide checkpoint granularity; a coordinator aligns checkpoints with turn boundaries and overlaps C/R with LLM wait time; and a host-scoped engine schedules checkpoint traffic across co-located sandboxes. On shell-intensive and code-repair workloads, Crab raises recovery correctness from 8% (chat-only) to 100%, cuts checkpoint traffic by up to 87%, and stays within 1.9% of fault-free execution time.

The standard post-training recipe for large multimodal models (LMMs) applies supervised fine-tuning (SFT) on curated demonstrations followed by reinforcement learning with verifiable rewards (RLVR). However, SFT introduces distributional drift that neither preserves the model's original capabilities nor faithfully matches the supervision distribution. This problem is further amplified in multimodal reasoning, where perception errors and reasoning failures follow distinct drift patterns that compound during subsequent RL. We introduce PRISM, a three-stage pipeline that mitigates this drift by inserting an explicit distribution-alignment stage between SFT and RLVR. Building on the principle of on-policy distillation (OPD), PRISM casts alignment as a black-box, response-level adversarial game between the policy and a Mixture-of-Experts (MoE) discriminator with dedicated perception and reasoning experts, providing disentangled corrective signals that steer the policy toward the supervision distribution without requiring access to teacher logits. While 1.26M public demonstrations suffice for broad SFT initialization, distribution alignment demands higher-fidelity supervision; we therefore curate 113K additional demonstrations from Gemini 3 Flash, featuring dense visual grounding and step-by-step reasoning on the hardest unsolved problems. Experiments on Qwen3-VL show that PRISM consistently improves downstream RLVR performance across multiple RL algorithms (GRPO, DAPO, GSPO) and diverse multimodal benchmarks, improving average accuracy by +4.4 and +6.0 points over the SFT-to-RLVR baseline on 4B and 8B, respectively. Our code, data, and model checkpoints are publicly available at https://github.com/XIAO4579/PRISM.

Modern visual world modeling systems increasingly rely on high-capacity architectures and large-scale data to produce plausible motion, yet they often fail to preserve underlying 3D geometry or physically consistent camera dynamics. A key limitation lies not only in model capacity, but in the latent representations used to encode geometric structure. We propose S$^2$VAE, a geometry-first latent learning framework that focuses on compressing and representing the latent 3D state of a scene, including camera motion, depth, and point-level structure, rather than modeling appearance alone. Building on representations from a Visual Geometry Grounded Transformer (VGGT), we introduce a novel type of variational autoencoder using a product of Power Spherical latent distributions, explicitly enforcing hyperspherical structure in the bottleneck to preserve directional and geometric semantics under strong compression. Across depth estimation, camera pose recovery, and point cloud reconstruction, we show that geometry-aligned hyperspherical latents consistently outperform conventional Gaussian bottlenecks, particularly in high-compression regimes. Our results highlight latent geometry as a first-class design choice for physically grounded visual and world models.

Transformer models are widely deployed in critical AI applications, yet faults in their attention mechanisms, projections, and other internal components often degrade behavior silently without raising runtime errors. Existing fault diagnosis techniques often target generic deep neural networks and cannot identify which transformer component is responsible for an observed symptom. In this article, we present DEFault++, a hierarchical learning-based diagnostic technique that operates at three level of abstraction: it detects whether a fault is present, classifies it into one of 12 transformer-specific fault categories (covering both attention-internal mechanisms and surrounding architectural components), and identifies the underlying root cause from up to 45 mechanisms. To facilitate both training and evaluation, we construct DEFault-bench, a benchmark of 3,739 labeled instances obtained through systematic mutation testing. These instances are created across seven transformer models and nine downstream tasks using DEForm, a transformer-specific mutation technique we developed for this purpose. DEFault++ measures runtime behavior at the level of individual transformer components. It organizes these measurements through a Fault Propagation Graph (FPG) derived from the transformer architecture. It then produces an interpretable diagnosis using prototype matching combined with supervised contrastive learning. On DEFault-bench, DEFault++ exceeds an AUROC of 0.96 for detection and a Macro-F1 of 0.85 for both categorization and root-cause diagnosis on encoder and decoder architectures. In a developer study with 21 practitioners, the accuracy of choosing correct repair actions increased from 57.1% without support to 83.3% when using DEFault++.

Existing learning-based occupancy prediction methods rely on large-scale 3D annotations and generalize poorly across environments. We present FreeOcc, a training-free framework for open-vocabulary occupancy prediction from monocular or RGB-D sequences. Unlike prior approaches that require voxel-level supervision and ground-truth camera poses, FreeOcc operates without 3D annotations, pose ground truth, or any learning stage. FreeOcc incrementally builds a globally consistent occupancy map via a four-layer pipeline: a SLAM backbone estimates poses and sparse geometry; a geometrically consistent Gaussian update constructs dense 3D Gaussian maps; open-vocabulary semantics from off-the-shelf vision-language models are associated with Gaussian primitives; and a probabilistic Gaussian-to-occupancy projection produces dense voxel occupancy. Despite being entirely training-free and pose-agnostic, FreeOcc achieves over $2\times$ improvements in IoU and mIoU on EmbodiedOcc-ScanNet compared to prior self-supervised methods. We further introduce ReplicaOcc, a benchmark for indoor open-vocabulary occupancy prediction, and show that FreeOcc transfers zero-shot to novel environments, substantially outperforming both supervised and self-supervised baselines. Project page: https://the-masses.github.io/freeocc-web/.

Accurate lesion segmentation is crucial for clinical diagnosis and treatment planning. However, lesions often resemble surrounding tissues and exhibit ill-defined boundaries, leading to unstable predictions in boundary/transition regions. Moreover, small-lesion cues can be diluted by multi-scale feature extraction, causing under- or over-segmentation. To address these challenges, we propose an Uncertainty-Aware Hypergraph Refinement Network (UHR-Net). First, we introduce an Uncertainty-Oriented Instance Contrastive (UO-IC) pretraining strategy that couples geometry-aware copy-paste augmentation with hard-negative mining of lesion-like background regions to improve instance-level discrimination for small and visually ambiguous lesions. Second, we design an Uncertainty-Guided Hypergraph Refinement (UGHR) block, which derives an entropy-based uncertainty map from a coarse probability map to guide hypergraph refinement. By splitting hyperedge prototypes into foreground and background groups, UGHR decouples higher-order interactions and improves refinement in ambiguous regions. Experiments on five public benchmarks demonstrate consistent gains over strong baselines. Code is available at: https://github.com/CUGfreshman/UHR-Net.

Terminal-agent benchmarks have become a primary signal for measuring the coding and system-administration capabilities of large language models. As the market for evaluation environments grows, so does the pressure to ship tasks quickly, often without thorough adversarial review of the verification logic. This paper is a guideline for writing good benchmark tasks, drawn from over a year of contributing to and reviewing tasks for Terminal Bench. Most people write benchmark tasks the way they write prompts. They shouldn't. A prompt is designed to help the agent succeed; a benchmark is designed to find out if it can. We argue that good tasks are adversarial, difficult, and legible, and that a large class of common failure modes -- AI-generated instructions, over-prescriptive specifications, clerical difficulty, oracle solutions that assume hidden knowledge, tests that validate the wrong things, and reward-hackable environments -- are predictable consequences of treating task authoring as prompt authoring. We catalog these failure modes, argue that real difficulty is conceptual rather than environmental, and discuss recent empirical evidence that over 15% of tasks in popular terminal-agent benchmarks are reward-hackable. We hope this serves as a useful reference for benchmark maintainers, task contributors, and researchers using benchmark scores as evidence.

The rapid electrification and intelligence of modern transportation systems place stringent demands on the electromagnetic compatibility, reliability, and adaptability of automotive power electronics. In electric and autonomous vehicles, electromagnetic interference (EMI) generated by high-frequency switching power converters can compromise safety-critical functions, in-vehicle communications, and system efficiency under dynamic operating conditions. Conventional passive EMI filters, while robust, are often oversized and lack adaptability, leading to increased weight, volume, and energy losses. This paper proposes an intelligent self-tuning active EMI filtering approach for electrified automotive power systems based on reinforcement learning (RL). The EMI mitigation problem is formulated as a Markov decision process, enabling an RL agent to continuously adapt filter parameters in response to time-varying interference characteristics. To improve robustness and generalisation under complex and non-stationary conditions, a variational autoencoder is employed for compact state representation, while a noise-based exploration mechanism enhances learning efficiency and prevents suboptimal convergence. The proposed method is evaluated using experimentally measured EMI spectra from an automotive electric drive unit within a MATLAB/Simulink co-simulation framework. Results demonstrate consistent EMI attenuation improvements of 25-30 dB across a wide frequency range compared with conventional control strategies and passive filtering solutions. By reducing reliance on oversized passive components and enabling adaptive EMI suppression, the proposed framework supports lightweight, energy-efficient, and reliable power-electronic systems for intelligent and green transportation applications.

Despite rapid advances in photorealistic video generation, real-world applications such as filmmaking require video aesthetics, e.g., harmonious colors and cinematic lighting, beyond visual fidelity. Prior work on visual aesthetics largely focuses on images, often reducing aesthetics to coarse definitions, e.g., visual pleasure, without a rigorous and systematic evaluation. To improve video aesthetics, we propose a hierarchical rubric that decomposes video aesthetics into three core dimensions, Visual Aesthetics (VA), Visual Fidelity (VF), and Visual Plausibility (VP), with 15 fine-grained criteria, e.g., shot composition. This framework enables a large-scale expert-annotated preference dataset and an evaluation benchmark, AesVideo-Bench, containing about 2500 video pairs with expert annotations on VA, VF, and VP. We then build a family of Video Aesthetic Reward Models (AesRM): AesRM-Base, which directly predicts pairwise preferences on these dimensions to provide efficient post-training rewards, and AesRM-CoT, which additionally generates CoT aligned with all 15 criteria to improve assessment interpretability. Specifically, we train AesRM with a three-stage progressive scheme: (1) Atomic Aesthetic Capability Learning, which strengthens AesRM's recognition of fundamental aesthetic concepts, e.g., accurately identifying centered composition; (2) Cold-Start, aligning the model with structured reasoning protocols; and (3) GRPO, further improving evaluation accuracy. To enhance AesRM-CoT, we additionally propose self-consistency-based CoT synthesis to improve CoT quality and design CoT-based process rewards during GRPO. Extensive experiments show AesRM outperforms baselines on multiple aesthetics benchmarks and is more robust, with lower position bias. Finally, we align Wan2.2 with AesRM and observe clear aesthetic gains over existing aesthetic reward models.

Large Language Models (LLMs) have advanced Table Question Answering, where most queries can be answered by extracting information or simple aggregation. However, a common class of real-world queries is implicitly predictive, requiring the inference of unobserved answers from historical patterns rather than mere retrieval. These queries introduce two challenges: recognizing latent intent and reliable predictive reasoning over massive tables. To assess LLMs in such Tabular questiOn answering with implicit Prediction tasks, we introduce TopBench, a benchmark consisting of 779 samples across four sub-tasks, ranging from single-point prediction to decision making, treatment effect analysis, and complex filtering, requiring models to generate outputs spanning reasoning text and structured tables. We evaluate diverse models under both text-based and agentic workflows. Experiments reveal that current models often struggle with intent recognition, defaulting to just lookups. Deeper analysis identifies that accurate intent disambiguation serves as the prerequisite for leading these predictive behaviors. Furthermore, elevating the upper bound of prediction precision requires the integration of more sophisticated modeling or reasoning capabilities.

Recent research has shown that filtering massive English web corpora into high-quality subsets significantly improves training efficiency. However, for high-resource non-English languages like German, French, or Japanese, aggressive filtering creates a strategic dilemma: should practitioners prioritize diversity by training once on large amounts of lightly filtered web data, or prioritize quality by strictly filtering for a high-quality core and repeating it over multiple epochs? We investigate this trade-off for German by constructing hierarchical quality filters applied to 500M web documents, comparing multi-epoch training on the filtered subsets against single-pass training on a diverse corpus. Our experiments across multiple model scales and token budgets show that repeating high-quality data consistently outperforms single-pass training on larger, less filtered sets. Notably, the performance gap persists even after 7 epochs. Our findings suggest that for non-English LLMs, semantic concentration through quality filtering offers a more viable path to efficient language modeling than simply maximizing unique data volume. We release our German language models (called Boldt), as well as our cleaned evaluation benchmarks to the research community. Our experiments indicate that they achieve state-of-the-art results despite training on 10-360x fewer tokens than comparable models.

To couple many independent modes from free space to on chip, the key challenge is not enhancing the many necessary coupling rates (scattering-matrix elements) between targeted mode pairs. Instead, the key is to avoid additional cross-couplings to undesired modes, due to the presence of multiple simultaneously satisfied phase-matching conditions. With this principle, we identify scaling laws for the maximum number of high-efficiency multi-mode couplings that may be achievable for a given refractive index and design region, which are strongly supported by extensive numerical inverse-design experiments in 2D (one-dimensional coupler patterns, scattering in 2D). For such couplers, typical mode counts of 5--10 appear achievable. Three-dimensional couplers (patterned across two dimensions) can be markedly better, with tens of Fourier components in a single-layer device offering the possibility of high-efficiency coupling of hundreds to thousands of modes in relatively compact form factors. Numerical simulations of such a device, without any parameter optimization, predict efficiencies on the order of 5\% for 100 modes -- a collective order-of-magnitude improvement over previous designs.

We apply a systematic inverse design approach to discover foundry-compliant, multilayer grating couplers that can efficiently couple a number of independent waves from free space to on-chip propagating modes. For visible- and near-infrared couplers, we find that minimum feature sizes are by far the most important constraint to tailor the design algorithms around. If, additionally, one forces the optimization to be robust to over- and under-etch errors, the resulting designs exhibit stable optimal efficiencies in the presence of other imperfections (critical dimension variations, overlay mismatch, and sidewall angle variation). The foundry-compliant designs exhibit moderate efficiency penalties as feature sizes increase, but no change to simple underlying scaling laws with respect to requisite numbers of layers and layer thicknesses. These results establish a practical, generalizable framework for high-efficiency multimode coupling within the constraints of modern semiconductor foundries.

Large language models (LLMs) make reward design in reinforcement learning substantially more scalable, but generated rewards are not automatically reliable training objectives. Existing work has focused primarily on generating, evolving, or selecting reward candidates, while paying less attention to when such candidates can be verified and deployed during policy optimization. We study this deployment-time problem by treating generated rewards as reward hypotheses whose utility depends on the competence of the current policy and the phase of training. We propose \textsc{RHyVE}, a competence-aware verification and phase-aware deployment protocol that compares small sets of reward hypotheses from shared policy checkpoints using short-horizon fork verification. Our experiments show that reward rankings are unreliable at low competence but become informative after task-dependent thresholds. On a sparse manipulation task, phase-aware deployment improves peak and retained performance under a locked protocol. Updated LLM-generated reward-candidate experiments show candidate-family-dependent behavior: generated pools can exhibit phase-dependent winner changes, but no fixed warm-up schedule is universally optimal. Held-out schedule selection, conservative selector baselines, compute-matched controls, and scale controls further show that \textsc{RHyVE} is best understood as a verification-informed deployment protocol rather than a universal scheduler. Dense and all-failure boundary experiments delimit the scope of the method. Together, these results suggest that reward generation and reward deployment should be studied as coupled problems: generated rewards must be verified and deployed under changing policy competence.

Text-to-SQL (T2SQL) evaluation in production environments poses fundamental challenges that existing benchmarks do not address. Current evaluation methodologies whether rule-based SQL matching or schema-dependent semantic parsers assume access to ground-truth queries and structured database schema, constraints that are rarely satisfied in real-world deployments. This disconnect leaves production T2SQL agents largely unevaluated beyond developer-time testing, creating silent quality degradation with no feedback mechanism for continuous improvement. We present STEF (Schema-agnostic Text-to-SQL Evaluation Framework), a production-native evaluation system that operates exclusively on natural language inputs the user question, an enriched reformulation, and the generated SQL without requiring database schema or reference queries. STEF extracts semantic specifications from both natural language and SQL representations, performs normalized feature alignment, and produces an interpretable 0 to 100 accuracy score via a composite metric that encompasses filter alignment, semantic verdict, and confidence of the evaluator. Key contributions include: enriched question quality validation as a first-class evaluation signal, configurable application-specific rule injection via prompt templating, and production-robust normalization handling GROUP BY tolerance, ORDER BY defaults, and LIMIT heuristics. Empirical results demonstrate that STEF enables continuous production monitoring and agent improvement feedback loops without schema dependency, making structured query evaluation viable at scale for the first time.

Large Language Models (LLMs) are increasingly used as proxies for human perception in urban analysis, yet it remains unclear whether persona prompting produces meaningful and reproducible behavioral diversity. We investigate whether distinct personas influence urban sentiment judgments generated by multimodal LLMs. Using a factorial set of personas spanning gender, economic status, political orientation, and personality, we instantiate multiple agents per persona to evaluate urban scene images from the PerceptSent dataset and assess both within-persona consistency and cross-persona variation. Results show strong convergence among agents sharing a persona, indicating stable and reproducible behavior. However, cross-persona differentiation is limited: economic status and personality induce statistically detectable but practically modest variation, while gender shows no measurable effect and political orientation only negligible impact. Agents also exhibit an extremity bias, collapsing intermediate sentiment categories common in human annotations. As a result, performance remains strong on coarse-grained polarity tasks but degrades as sentiment resolution increases, suggesting that simple label-based persona prompting does not capture fine-grained perceptual judgments. To isolate the contribution of persona conditioning, we additionally evaluate the same model without personas. Surprisingly, the no-persona model sometimes matches or exceeds persona-conditioned agreement with human labels across all task variants, suggesting that simple label-based persona prompting may add limited annotation value in this setting.

We present Collaborative Agent Reasoning Engineering (CARE), a disciplined methodology for engineering Large Language Model (LLM) agents in scientific domains. Unlike ad-hoc trial-and-error approaches, CARE specifies behavior, grounding, tool orchestration, and verification through reusable artifacts and systematic, stage-gated phases. The methodology employs a three-party workflow involving Subject-Matter Experts (SMEs), developers, and LLM-based helper agents. These helper agents function as facilitation infrastructure, transforming informal domain intent into structured, reviewable specifications for human approval at defined gates. CARE addresses the "jagged technological frontier", characterized by uneven LLM performance, by bridging the gap between novice and expert analysts regarding domain constraints and verification practices. By generating concrete artifacts, including interaction requirements, reasoning policies, and evaluation criteria, CARE ensures agent behavior is specifiable, testable, and maintainable. Evaluation results from a scientific use case demonstrate that this stage-gated, artifact-driven methodology yields measurable improvements in development efficiency and complex-query performance.

Spectra are a prevalent yet highly information-dense form of scientific imagery, presenting substantial challenges to multimodal large language models (MLLMs) due to their unstructured and domain-specific characteristics. Here we introduce SpecVQA, a professional scientific-image benchmark for evaluating multimodal models on scientific spectral understanding, covering 7 representative spectrum types with expert-annotated question-answer pairs. The aim comprises two aspects: spectra scientific QA evaluation and corresponding underlying task evaluation. SpecVQA contains 620 figures and 3100 QA pairs curated from peer-reviewed literature, targeting both direct information extraction and domain-specific reasoning. To effectively reduce token length while preserving essential curve characteristics, we propose a spectral data sampling and interpolation reconstruction approach. Ablation studies further confirm that the approach achieves substantial performance improvements on the proposed benchmark. We test the capability of prominent MLLMs in scientific spectral understanding on our benchmark and present a leaderboard. This work represents an essential step toward enhancing spectral understanding in multimodal large models and suggests promising directions for extending visual-language models to broader scientific research and data analysis.

When researchers iteratively refine ideas with large language models, do the models preserve fidelity to the original objective? We introduce DriftBench, a benchmark for evaluating constraint adherence in multi-turn LLM-assisted scientific ideation. Across 2,146 scored benchmark runs spanning seven models from five providers (including two open-weight), four interaction conditions, and 38 research briefs from 24 scientific domains, we find that iterative pressure reliably increases structural complexity and often reduces adherence to original constraints. A restatement probe reveals a dissociation between declarative recall and behavioral adherence, as models accurately restate constraints they simultaneously violate. The knows-but-violates (KBV) rate, measuring constraint non-compliance despite preserved recall, ranges from 8% to 99% across models. Structured checkpointing partially reduces KBV rates but does not close the dissociation, and complexity inflation persists. Human validation against blind raters confirms that the LLM judge under-detects constraint violations, making reported constraint adherence scores conservative. Sensitivity analyses confirm the findings are robust to temperature (0.7 vs.\ 1.0) and pressure type (novelty vs.\ rigor). We release all briefs, prompts, rubrics, transcripts, and scores as an open benchmark.

Fairness in machine learning remains challenging due to its ethical complexity, the absence of a universal definition, and the need for context-specific bias metrics. Existing methods still struggle with intersectionality, multiclass settings, and limited flexibility and generality. To address these gaps, we introduce MIFair, a unified framework for bias assessment and mitigation based on mutual information. MIFair provides a flexible metric template and an in-processing mitigation method inspired by the Prejudice Remover, defining group fairness as statistical independence between prediction-derived variables and sensitive attributes. We further strengthen its information-theoretic foundation by establishing equivalences with widely used fairness notions such as independence and separation. MIFair naturally supports intersectionality, complex subgroup structures, and multiclass classification and employs regularization-based training to reduce bias according to the selected metric. Its key advantage is its versatility: it consolidates diverse fairness requirements into a single coherent framework, enabling consistent benchmarking and simplifying practical use. Experiments on real-world tabular and image datasets show that MIFair effectively reduces bias, including previously unaddressed multi-attribute scenarios, while maintaining strong predictive performance across the evaluated settings.

Current DeepFake detection scenarios are mostly binary, yet data manipulation can vary across audio, video, or both, whose variability is not captured in binary settings. Four-class audio-visual formulations address this by discriminating manipulation type, but introduce a unresolved problem: models may rely solely on data source integrity to detect DeepFakes without evaluating their semantic consistency. If the DeepFake origin is not in the data source but in its content, can semantic mismatch be assessed by the state-of-the-art? This paper proposes a new evaluation setup, extending the four-class formulation by explicitly modeling semantic-level inconsistency between authentic modalities with the introduction a new class: Real Audio-Real Video with Semantic Mismatch (RARV-SMM). We assess the robustness of state-of-the-art models in this new realistic DeepFake setting, using the FakeAVCeleb dataset, highlighting the limitations of existing approaches when faced with semantic mismatch data. We further introduce three RARV-SMM variants that expose distinct architectural vulnerabilities as audio-visual divergence increases. We also propose a semantic reinforcement strategy that incorporates the semantic mismatch class and ImageBind embeddings to improve DeepFake detection in both our proposed and state-of-the-art settings, on FakeAVCeleb and LAV-DF, paving the way to more realistic DeepFake detectors. The source code and data are available at https://github.com/.

3D Gaussian Splatting has emerged as a powerful scene representation for real-time novel-view synthesis. However, its standard adaptive density control relies on screen-space positional gradients, which do not distinguish between geometric misplacement and frequency aliasing, often leading to either over-blurred high-frequency textures or inefficient over-densification. We present a structure-aware densification framework. Our key insight is that the decision to subdivide a Gaussian should be driven by an explicit comparison between its projected screen-space extent and the local structure of the texture it seeks to represent. We introduce a multi-scale frequency analysis combining structure tensors with Laplacian scale space analysis to estimate the dominant frequency at each pixel, enabling robust supervision across varying texture scales. Based on this analysis, we define $η$, a per-Gaussian, per-axis frequency violation metric that indicates when a primitive may be under-resolving local texture details. Unlike methods that perform isotropic splitting (e.g., splitting each Gaussian into two smaller ones with uniform shape), our approach performs anisotropic splitting. For each axis with high $η$, we compute a split factor to better resolve the local frequency content. We further introduce a multiview consistency criterion that aggregates $η$ observations across multiple views. By performing densification early and faster, we skip the lengthy iterative densification phases required by baseline methods and achieve significantly faster convergence. Experiments on standard benchmarks demonstrate that our method also achieves superior reconstruction quality, particularly in high-frequency regions.

Ultrasound interpretation requires both precise lesion localization and holistic clinical reasoning, yet existing methods typically excel at only one of these capabilities: specialized detectors offer strong localization but limited reasoning, whereas multimodal large language models (MLLMs) provide flexible reasoning but weak grounding in specialized medical domains. We present Echo-α, an agentic multimodal reasoning model for ultrasound interpretation that unifies these strengths within an invoke-and-reason framework. Echo-α is trained to coordinate organ-specific detector outputs, integrate them with global visual context, and convert the resulting evidence into grounded diagnostic decisions beyond detector-only inference. This behavior is established through a nine-task supervised curriculum and then refined by sequential reinforcement learning under different reward trade-offs, yielding Echo-α-Grounding for lesion anchoring and Echo-α-Diagnosis for final diagnosis. On multi-center renal and breast ultrasound benchmarks, Echo-α outperforms competitive baselines on both grounding and diagnosis. In particular, on cross-center test sets, Echo-α-Grounding attains 56.73%/43.78% F1@0.5 and Echo- α-Diagnosis reaches 74.90%/49.20% overall accuracy on renal/breast ultrasound. These results suggest that agentic multimodal reasoning can turn specialized detectors into verifiable clinical evidence, offering a practical route toward ultrasound AI systems that are more accurate, interpretable, and transferable. The repository is at https://github.com/MiliLab/Echo-Alpha.

Integrating multimodal foundation models into enterprise ecosystems presents a fundamental software architecture challenge. Architects must balance competing quality attributes: the high latency and non-determinism of vision language action (VLA) models versus the strict determinism and real-time performance required by enterprise control loops. In this study, we propose an architectural pattern language for visual agents that separates fast, deterministic reflexes from slow, probabilistic supervision. It consists of four architectural design patterns: (1) Hybrid Affordance Integration, (2) Adaptive Visual Anchoring, (3) Visual Hierarchy Synthesis, and (4) Semantic Scene Graph.

Latent reasoning offers a more efficient alternative to explicit reasoning by compressing intermediate reasoning into continuous representations and substantially shortening reasoning chains. However, existing latent reasoning methods mainly focus on supervised learning, and reinforcement learning in latent space remains highly unstable. We study this problem through the lens of Group Relative Policy Optimization (GRPO), and show that directly adapting GRPO to latent reasoning is fundamentally non-trivial: latent reasoning changes both the probability density and the sampling mechanism, causing three coupled bottlenecks: absence of intrinsic latent manifolds, where unconstrained exploration pushes rollouts off the valid latent manifold; exploration-optimization misalignment, where trajectory-level rewards can induce incorrect token-level updates; and latent mixture non-closure, where jointly reinforcing multiple correct latent paths can produce an invalid averaged state. To address them, we propose \textbf{Latent-GRPO}, which combines invalid-sample advantage masking, one-sided noise sampling, and optimal correct-path first-token selection. Across four low-difficulty benchmarks (e.g., GSM8K-Aug) and four high-difficulty benchmarks (e.g., AIME), Latent-GRPO improves over its latent initialization by 7.86 Pass@1 points on low-difficulty tasks and surpasses explicit GRPO by 4.27 points on high-difficulty tasks while using 3--4$\times$ shorter reasoning chains. It also achieves stronger pass@$k$ performance under Gumbel sampling. These results establish Latent-GRPO as an effective approach for stable and efficient latent reasoning.

This paper examines how different types of large language model (LLM) agents perform on scientific visualization (SciVis) tasks, where users generate visualization workflows from natural-language instructions. We compare three primary interaction paradigms, including domain-specific agents with structured tool use, computer-use agents, and general-purpose coding agents, by evaluating eight representative agents across 15 benchmark tasks and measuring visualization quality, efficiency, robustness, and computational cost. We further analyze interaction modalities, including code scripts and model context protocol (MCP) or API calls for structured tool use, as well as command-line interfaces (CLI) and graphical user interfaces (GUI) for more general interaction, while additionally studying the effect of persistent memory in selected agents. The results reveal clear tradeoffs across paradigms and modalities. General-purpose coding agents achieve the highest task success rates but are computationally expensive, while domain-specific agents are more efficient and stable but less flexible. Computer-use agents perform well on individual steps but struggle with longer multi-step workflows, indicating that long-horizon planning is their primary limitation. Across both CLI- and GUI-based settings, persistent memory improves performance over repeated trials, although its benefits depend on the underlying interaction mode and the quality of feedback. These findings suggest that no single approach is sufficient, and future SciVis systems should combine structured tool use, interactive capabilities, and adaptive memory mechanisms to balance performance, robustness, and flexibility.

Multivariate time series forecasting plays a pivotal role in numerous real-world applications, including financial analysis, energy management, and traffic planning. While Transformer-based architectures have gained popularity for this task, recent studies reveal that simpler MLP-based models can achieve competitive or superior performance with significantly reduced computational cost. In this paper, we propose ITS-Mina, a novel all-MLP framework for multivariate time series forecasting that integrates three key innovations: (1) an iterative refinement mechanism that progressively enhances temporal representations by repeatedly applying a shared-parameter residual mixer stack, effectively deepening the model's computational capacity without multiplying the number of distinct parameters; (2) an external attention module that replaces traditional self-attention with learnable memory units, capturing cross-sample global dependencies at linear computational complexity; and (3) a Harris Hawks Optimization (HHO) algorithm for automatic dropout rate tuning, enabling adaptive regularization tailored to each dataset. Extensive experiments on six widely-used benchmark datasets demonstrate that ITS-Mina achieves state-of-the-art or highly competitive performance compared to eleven baseline models across multiple forecasting horizons.

Traditional Shot Boundary Detection (SBD) inherently struggles with complex transitions by formulating the task around isolated cut points, frequently yielding corrupted video shots. We address this fundamental limitation by formalizing the Shot Transition Detection (STD) task. Rather than searching for ambiguous points, STD explicitly detects the continuous temporal segments of transitions. To tackle this, we propose TransVLM, a Vision-Language Model (VLM) framework for STD. Unlike regular VLMs that predominantly rely on spatial semantics and struggle with fine-grained inter-shot dynamics, our method explicitly injects optical flow as a critical motion prior at the input stage. Through a simple yet effective feature-fusion strategy, TransVLM directly processes concatenated color and motion representations, significantly enhancing its temporal awareness without incurring any additional visual token overhead on the language backbone. To overcome the severe class imbalance in public data, we design a scalable data engine to synthesize diverse transition videos for robust training, alongside a comprehensive benchmark for STD. Extensive experiments demonstrate that TransVLM achieves superior overall performance, outperforming traditional heuristic methods, specialized spatiotemporal networks, and top-tier VLMs. This work has been deployed to production. For more related research, please visit HeyGen Research (https://www.heygen.com/research) and HeyGen Avatar-V (https://www.heygen.com/research/avatar-v-model). Project page: https://chence17.github.io/TransVLM/

Despite the rapid progress of large vision-language models (LVLMs), fine-grained, state-conditioned GUI interaction remains challenging. Current evaluations offer limited coverage, imprecise target-state definitions, and an overreliance on final-task success, obscuring where and why agents fail. To address this gap, we introduce \textbf{FineState-Bench}, a benchmark that evaluates whether an agent can correctly ground an instruction to the intended UI control and reach the exact target state. FineState-Bench comprises 2,209 instances across desktop, web, and mobile platforms, spanning four interaction families and 23 UI component types, with each instance explicitly specifying an exact target state for fine-grained state setting. We further propose \textit{FineState-Metrics}, a four-stage diagnostic pipeline with stage-wise success rates: Localization Success Rate (SR@Loc), Interaction Success Rate (SR@Int), Exact State Success Rate at Locate (ES-SR@Loc), and Exact State Success Rate at Interact (ES-SR@Int), and a plug-and-play \textit{Visual Diagnostic Assistant} (VDA) that generates a Description and a bounding-box Localization Hint to diagnose visual grounding reason via controlled w/ vs.\ w/o comparisons. On FineState-Bench, exact goal-state success remains low: ES-SR@Int peaks at 32.8\% on Web and 22.8\% on average across platforms. With VDA localization hints, Gemini-2.5-Flash gains +14.9 ES-SR@Int points, suggesting substantial headroom from improved visual grounding, yet overall accuracy is still insufficient for reliable fine-grained state-conditioned interaction \href{https://github.com/FengxianJi/FineState-Bench}{Github.}

The pervasive growth of digital content, specifically short videos on social media platforms, has significantly altered how topics are discussed and understood in public discourse. In this work, we advance automated visual theme detection by assessing zero-shot and clustering capabilities on social media data. (1) We evaluated the capabilities of notable VLMs such as VideoChatGPT, PandaGPT, and VideoLLava using zero-shot image classification and compared their performance to the baseline provided by frame-wise CLIP image classification. (2) By treating clustering as a minimum cost multicut problem, we aim to uncover insightful patterns in an unsupervised manner. For both analysis strategies, we provide extensive evaluations and practical guidance to practitioners. While VLMs are currently not able to detect climate change specific classes, the clustering results are distinct visual frames. %Given that VLMs are not currently capable to grasp the climate change discourse, we focus the clustering evaluation of image embedding models. We find that both ConvNeXt V2 and DINOv2 produce meaningful clusters, with DINOv2 focusing more on style differences and abstract categories, while ConvNeXt V2 clusters differ in more fine-grained ways. Code available at https://github.com/KathPra/ClimateVID.git.

Designing mechanical linkages involves combinatorial topology selection and continuous parameter fitting. We show that language models can systematically improve linkage designs through symbolic representations. Language model agents explore discrete topologies while numerical optimisers fit continuous parameters. A symbolic lifting operator translates simulator trajectories into qualitative descriptors, motion labels, temporal predicates, and structural diagnostics that models interpret across iterative design cycles. Across six engineering-relevant motion targets and three open-source models (Llama 3.3 70B, Qwen3 4B, Qwen3 MoE 30B-A3B), the modular architecture reduces geometric error by up to 68% and improves structural validity by up to 134% over monolithic baselines. Critically, 78.6% of iterative refinement trajectories show measurable improvement, with the system correctly diagnosing overconstraint (56.3%) and underconstraint (35.6%) failure modes and proposing grounded corrections. Models across all three families acquire interpretable mechanical reasoning strategies without fine-tuning, demonstrating that principled symbolic abstraction bridges generative AI and the numerical precision required for engineering design.

Recent large language models (LLMs) have achieved impressive reasoning milestones but continue to struggle with high computational costs, logical inconsistencies, and sharp performance degradation on high-complexity problems. While neuro-symbolic methods attempt to mitigate these issues by coupling LLMs with symbolic reasoners, existing approaches typically rely on monotonic logics (e.g., SMT) that cannot represent defeasible reasoning -- essential components of human cognition. We present "LLM+ASP," a framework that translates natural language into Answer Set Programming (ASP), a nonmonotonic formalism based on stable model semantics. Unlike prior "LLM+ASP" approaches that require manually authored knowledge modules, domain-specific prompts, or evaluation restricted to single problem classes, our framework operates without any per-task engineering and applies uniformly across diverse reasoning tasks. Our system utilizes an automated self-correction loop where structured feedback from the ASP solver enables iterative refinement. Evaluating across six diverse benchmarks, we demonstrate that: (1) stable model semantics allow LLMs to naturally express default rules and exceptions, outperforming SMT-based alternatives by significant margins on nonmonotonic tasks; (2) iterative self-correction is the primary driver of performance, effectively replacing the need for handcrafted domain knowledge; (3) compact in-context reference guides substantially outperform verbose documentation, revealing a "context rot" phenomenon where excessive context hinders constraint adherence.

Due to the scarcity of large-scale in-the-wild triplet data and the improper use of masks, the performance of video virtual try-on models remains limited. In this paper, we first introduce **TripVVT-10K**, the largest and most diverse in-the-wild triplet dataset to date, providing explicit video-level cross-garment supervision that existing video datasets lack. Built upon this resource, we develop **TripVVT**, a Diffusion Transformer-based framework that replaces fragile garment masks with a simple, stable human-mask prior, enabling reliable background preservation while remaining robust to real-world motion, occlusion, and cluttered scenes. To support comprehensive evaluation, we further establish **TripVVT-Bench**, a 100-case benchmark covering diverse garments, complex environments, and multi-person scenarios, with metrics spanning video quality, try-on fidelity, background consistency, and temporal coherence. Compared to state-of-the-art academic and commercial systems, TripVVT achieves superior video quality and garment fidelity while markedly improving generalization to challenging in-the-wild videos. We publicly release the dataset and benchmark, which we believe provide a solid foundation for advancing controllable, realistic, and temporally stable video virtual try-on.

As Vision-Language Models (VLMs) become increasingly integrated into decision-making systems, it is essential to understand how visual inputs influence their behavior. This paper investigates the effects of visual priming on VLMs' cooperative behavior using the Iterated Prisoner's Dilemma (IPD) as a test scenario. We examine whether exposure to images depicting behavioral concepts (kindness/helpfulness vs. aggressiveness/selfishness) and color-coded reward matrices alters VLM decision patterns. Experiments were conducted across multiple state-of-the-art VLMs. We further explore mitigation strategies including prompt modifications, Chain of Thought (CoT) reasoning, and visual token reduction. Results show that VLM behavior can be influenced by both image content and color cues, with varying susceptibility and mitigation effectiveness across models. These findings not only underscore the importance of robust evaluation frameworks for VLM deployment in visually rich and safety-critical environments, but also highlight how architectural and training differences among models may lead to distinct behavioral responses-an area worthy of further investigation.

In this paper an attractor FCM is created, tested, and analyzed. This FCM is neither a hebbian based nor agentic, nor a hybrid; it rather is a gradient descent based, physics constrained, Jacobian version of an FCM. Moreover, this model has several quirks; it uses residual memory, back propagation through time, and a fixed point anchor that is recursively implemented to update its weights. The residuals update the recursive part without losing the system memory. The model's anchor enables it to converge in a fixed point for which back propagation through time unrolls it and ensures that the error minimization is for an accurate gradient. Furthermore, a new learning algorithm is utilized. The Newton's method finds the system's fixed point attractor and then gradient descend is adaptively changing the landscape; an adaptive term is used to directly manipulate the weights through the attractor dynamics. As the adaptive term changes, the descent through the landscape is constantly adjusting according to sigmoid saturation, and that prevents premature convergence to a local minimum. Lastly, the updates are filtered by causal mask that informs the network about the physics, respecting the initial expert based opinions, for which model reduces the error to the target in an efficient way.

Collective intelligence emerges across biological, physical, and artificial systems without central coordination, yet a unifying principle governing such behaviour remains elusive. The Free Energy Principle explains how individual agents adapt through variational inference, while game theory formalises strategic interactions. Here we introduce the Game-Theoretic Free Energy Principle, a unified framework showing that multi-agent systems performing local free-energy minimisation implicitly implement a stochastic game. We prove that, under bounded rationality and local information constraints, stationary points of collective free energy correspond to approximate Nash equilibria of an induced game. Conversely, a broad class of cooperative games admits a variational representation in which equilibria arise as Gibbs distributions over coalitions, establishing a bridge between Bayesian inference and strategic interaction. To characterise higher-order effects, we introduce a free-energy formulation of the Harsanyi dividend, isolating irreducible multi-agent synergy. This yields a predictive theory of cooperation, including a falsifiable non-monotonic relationship between sensory precision and agent influence. We validate this prediction across neural, biological, and artificial multi-agent systems. These results identify a common variational principle underlying inference, thermodynamics, and game-theoretic equilibrium.

This paper presents an expert-guided active-inference-inspired framework for adaptive UAV swarm trajectory planning. The proposed method converts multi-UAV trajectory design from a repeated combinatorial optimization problem into a hierarchical probabilistic inference problem. In the offline phase, a genetic-algorithm planner with repulsive-force collision avoidance (GA--RF) generates expert demonstrations, which are abstracted into Mission, Route, and Motion dictionaries. These dictionaries are used to learn a probabilistic world model that captures how expert mission allocations induce route orders and how route orders induce motion-level behaviors. During online operation, the UAV swarm evaluates candidate actions by forming posterior beliefs over symbolic states and minimizing KL-divergence-based abnormality indicators with respect to expert-derived reference distributions. This enables mission allocation, route insertion, motion adaptation, and collision-aware replanning without rerunning the offline optimizer. Bayesian state estimators, including EKF and PF modules, are integrated at the motion level to improve trajectory correction under uncertainty. Simulation results show that the proposed framework preserves expert-like planning structure while producing smoother and more stable behavior than modified Q-learning. Additional validation using real-flight UAV trajectory data demonstrates that the learned world model can correct symbolic predictions under noisy and non-smooth observations, supporting its applicability to adaptive UAV swarm autonomy.

Multimodal Stance Detection (MSD) is crucial for understanding public discourse, yet effectively fusing text and image, especially with conflicting signals, remains challenging. Existing methods often face difficulties with contextual grounding, cross-modal interpretation ambiguity, and single-pass reasoning fragility. To address these, we propose Retrieval-Augmented Multi-modal Multi-agent Stance Detection (MM-StanceDet), a novel multi-agent framework integrating Retrieval Augmentation for contextual grounding, specialized Multimodal Analysis agents for nuanced interpretation, a Reasoning-Enhanced Debate stage for exploring perspectives, and Self-Reflection for robust adjudication. Extensive experiments on five datasets demonstrate MM-StanceDet significantly outperforms state-of-the-art baselines, validating the efficacy of its multi-agent architecture and structured reasoning stages in addressing complex multimodal stance challenges.

This paper studies data-driven approaches to the continuous-time linear quadratic regulator (LQR) problem based on two existing parameterizations, namely a closed-loop (CL) parameterization from behavioral system theory and an integral reinforcement learning (IRL) parameterization. The CL parameterization characterizes the closed-loop system via a matrix that satisfies equality constraints. While this parameterization has been extensively studied for discrete-time systems, we adapt key results to the continuous-time setting and develop a policy iteration (PI) scheme, derive a data-driven continuous-time algebraic Riccati equation (CARE), and introduce an alternative convex problem formulation. The IRL parameterization utilizes off-policy data to perform policy evaluation, which is then used for PI or value iteration. Within the IRL framework, we derive a policy gradient flow and propose convex reformulations of the LQR problem. Finally, we provide a unified treatment of these parameterizations that enables a systematic understanding of existing approaches and clarifies their structural relationships.

Existing talking avatar methods typically adopt an image-to-video pipeline conditioned on a static reference image within the same scene as the target generation. This restricted, single-view perspective lacks sufficient temporal and expression cues, limiting the ability to synthesize high-fidelity talking avatars in customized backgrounds. To this end, we introduce Talking Avatar generation from Video Reference (TAVR), a novel framework that shifts the paradigm by leveraging cross-scene video inputs. To effectively process these extended temporal contexts and bridge cross-scene domain gaps, TAVR integrates a token selection module alongside a comprehensive three-stage training scheme. Specifically, same-scene video pretraining establishes foundational appearance copying, which is subsequently expanded by cross-scene reference fine-tuning for robust cross-scene adaptation. Finally, task-specific reinforcement learning aligns the generated outputs with identity-based rewards to maximize identity similarity. To systematically evaluate cross-scene robustness, we construct a new benchmark comprising 158 carefully curated cross-scene video pairs. Extensive experiments show that TAVR benefits from flexible inference-time video referencing and consistently surpasses existing baselines both quantitatively and qualitatively. This work has been deployed to production. For more related research, please visit \href{https://www.heygen.com/research}{HeyGen Research} and \href{https://www.heygen.com/research/avatar-v-model}{HeyGen Avatar-V}.

When language models lack relevant knowledge for a given query, they frequently generate plausible responses that can be hallucinations, rather than admitting being agnostic about the answer. Retraining models to reward admitting ignorance can lead to overly conservative behaviors and poor generalization due to scarce evaluation benchmarks. We propose a post hoc framework, Conformal Abstention (CA), adapted from conformal prediction (CP) to determine whether to abstain from answering a query. CA provides finite-sample guarantees on both the probability of participation (i.e., not abstaining) and the probability that the generated response is correct. Importantly, the abstention decision relies on prediction confidence rather than the non-conformity scores used in CP, which are intractable for open-ended generation. To better align prediction confidence with the model's ignorance, we introduce a calibration strategy using representation geometry within the model to measure knowledge involvement in shaping the response. Experiments demonstrate that we improve selective answering significantly with 75 percent conditional correctness.

Persistent AI memory is often reduced to a retrieval problem: store prior interactions as text, embed them, and ask the model to recover relevant context later. This design is useful for thematic recall, but it is mismatched to the kinds of memory that agents need in production: exact facts, current state, updates and deletions, aggregation, relations, negative queries, and explicit unknowns. These operations require memory to behave less like search and more like a system of record. This paper argues that reliable external AI memory must be schema-grounded. Schemas define what must be remembered, what may be ignored, and which values must never be inferred. We present an iterative, schema-aware write path that decomposes memory ingestion into object detection, field detection, and field-value extraction, with validation gates, local retries, and stateful prompt control. The result shifts interpretation from the read path to the write path: reads become constrained queries over verified records rather than repeated inference over retrieved prose. We evaluate this design on structured extraction and end-to-end memory benchmarks. On the extraction benchmark, the judge-in-the-loop configuration reaches 90.42% object-level accuracy and 62.67% output accuracy, above all tested frontier structured-output baselines. On our end-to-end memory benchmark, xmemory reaches 97.10% F1, compared with 80.16%-87.24% across the third-party baselines. On the application-level task, xmemory reaches 95.2% accuracy, outperforming specialised memory systems, code-generated Markdown harnesses, and customer-facing frontier-model application harnesses. The results show that, for memory workloads requiring stable facts and stateful computation, architecture matters more than retrieval scale or model strength alone.

The rapid evolution of generative models has enabled the creation of highly realistic and diverse synthetic images, posing significant challenges to reliable and generalizable Synthetic Image Detection (SID). However, existing detectors are typically trained on limited and biased datasets, resulting in poor generalization to unseen generators. To address this issue, we propose HiMix, a unified framework that enhances generalization by expanding the training distribution and promoting artifact-aware representations. Specifically, the Mixup-driven Distributional Augmentation (MDA) module constructs continuous transitional samples between real and fake images, improving coverage of low-confidence regions and exposing the model to more challenging samples, while the pixel-wise mixup operation smoothly perturbs semantics to enhance sensitivity to low-level artifacts. Moreover, the Hierarchical Artifact-aware Representation (HAR) module aggregates artifact information from both global and local levels through cross-layer integration and coarse-to-fine feature fusion, enabling the extraction of discriminative forgery representations under diverse distributions. Extensive experiments across multiple benchmarks demonstrate that HiMix achieves state-of-the-art performance, establishing well-separated logits for improved generalization to unseen forgeries.

Understanding how human health changes over time, and why responses to interventions vary between individuals, remains a central challenge in medicine. Here we present HealthFormer, a decoder-only transformer that models the human physiological trajectory generatively, by training on data from the Human Phenotype Project, a multi-visit cohort of over 15,000 deeply phenotyped individuals. We tokenise each participant's health trajectory across 667 measurements spanning seven domains: blood biomarkers, body composition, sleep physiology, continuous glucose monitoring, gut microbiome, wearable-derived physiology, and behaviour and medication exposure. We train HealthFormer to forecast individual physiological trajectories across these domains, and from this single generative objective a range of clinically relevant tasks can be expressed as queries on the model. We show that, without task-specific training, HealthFormer transfers to four independent cohorts and improves prediction for 27 of 30 incident-disease and mortality endpoints, exceeding established clinical risk scores in every comparison. We further show that the model can simulate interventions in silico: in a held-out personalised-nutrition trial, intervention-conditioned predictions recover individual six-month biomarker changes (e.g., Pearson r = 0.78 for diastolic blood pressure). Across 41 randomised intervention-outcome comparisons drawn from published trials, our results show that the predicted direction of effect agrees in every case, and the predicted mean falls within the reported 95% confidence interval in 30 cases. We position HealthFormer as an initial health world model, from which forecasting, risk stratification, and intervention-conditioned simulation arise as queries, providing a basis for clinical digital twins.

As one of the mainstream models of artificial intelligence, world models allow agents to learn the representation of the environment for efficient prediction and planning. However, classical world models based on flat tensors face several key problems, including noise sensitivity, error accumulation and weak reasoning. To address these limitations, many recent studies use graph structure to decompose the environment into entity nodes and interactive edges, and model virtual environments in a structured space. This paper systematically formalizes and unifies these emerging graph-based works under the concept of graph world models (GWMs). To the best of our knowledge, GWMs have not yet been explicitly defined and surveyed as a unified research paradigm. Furthermore, we propose a taxonomy based on relational inductive biases (RIB), categorizing GWMs by the specific structural priors they inject: (1) spatial RIB for topological abstraction; (2) physical RIB for dynamic simulation; and (3) logical RIB for causal and semantic reasoning. For each model category, we outline the key design principles, summarize representative models, and conduct comparative analyses. We further discuss open challenges and future directions, including dynamic graph adaptation, probabilistic relational dynamics, multi-granularity inductive biases, and the need for dedicated benchmarks and evaluation metrics for GWMs.

Agent orchestration frameworks -- LangGraph, CrewAI, Google ADK, OpenAI Agents SDK, and others -- place an external orchestrator above the LLM, tracking state and injecting routing instructions at every turn. We present a controlled comparison showing that for procedural tasks, this architecture is dominated by a simpler alternative: putting the entire procedure in the system prompt and letting the model self-orchestrate. Across three domains -- travel booking (14 nodes), Zoom technical support (14 nodes), and insurance claims processing (55 nodes) -- we evaluate 200 conversations per condition using LLM-as-judge scoring on five quality criteria. The in-context approach scores 4.53--5.00 on a 5-point scale while a LangGraph orchestrator using the same model scores 4.17--4.84. The orchestrated system fails on 24% of travel, 9% of Zoom, and 17% of insurance conversations, compared to 11.5%, 0.5%, and 5% for the in-context baseline. While external orchestration may have been necessary for earlier models, advances in frontier model capabilities have made it unnecessary for multi-turn conversations following a defined procedure.

Recent advances in agentic AI are shifting automation from discrete tools to proactive multi-agent systems that coordinate multi-specialized capabilities behind unified interfaces. However, today's agent systems typically rely on hard-coded agent architectures with fixed roles, coordination patterns, and interaction flows that limit end-user personalization and make adaptation to individual needs and contexts difficult. Given this limitation, we argue that on-demand persona-based agent generation offers a promising path towards more efficient and contextually appropriate interaction within agentic workflows. By dynamically crafting agents and personas at run-time to match user characteristics, task demands, and workflow context, agentic platforms can move beyond one-size-fits-all configurations. We present a pipeline for on-demand persona generation in agentic platforms, detailing how real-time crafting of AI personas can be systematically integrated within agent systems, aiming to open new possibilities in agentic platform design paradigms.

Large language model (LLM) agents deployed in clinical settings often exhibit abrupt, threshold-driven behavior, offering little visibility into accumulating risk prior to escalation. In real-world care, however, clinicians act on gradually rising concern rather than instantaneous triggers. We study whether explicit state dynamics can expose such pre-escalation signals without delegating clinical authority to the agent. We introduce a lightweight agent architecture in which a memoryless clinical risk encoder is integrated over time using first- and second-order dynamics to produce a continuous escalation pressure signal. Across synthetic ward scenarios, stateless agents exhibit sharp escalation cliffs, while second-order dynamics produce smooth, anticipatory concern trajectories despite similar escalation timing. These trajectories surface sustained unease prior to escalation, enabling human-in-the-loop monitoring and more informed intervention. Our results suggest that explicit state dynamics can make LLM agents more clinically legible by revealing how long concern has been rising, not just when thresholds are crossed.

Language models are saturating benchmarks for procedural tasks with narrow objectives. But they are increasingly being deployed in long-horizon, non-stationary environments with open-ended goals. In this paper we introduce KellyBench, an environment for evaluating sequential decision-making in sports betting markets. Agents are placed in a sequential simulation of the 2023-24 English Premier League season and tasked with maximising their long-term bankroll growth. They are given detailed historical data, including advanced statistics, lineups, and public odds. To succeed they must build machine learning models, identify edge in public markets, and adapt as the environment changes over time. We find that all frontier models evaluated lose money on average over the course of the season for five seeds. The best performing model achieves an average return of -8%, and many models experiencing ruin across seeds. To judge strategy sophistication, we use a human expert rubric to grade each model and find their approaches to be unsophisticated compared to human baselines; Claude Opus 4.6 achieves a rubric score of 26.5%, which means there is significant room for improvement. KellyBench is available as an open-access API endpoint at https://openreward.ai/GeneralReasoning/KellyBench.

Reinforcement Learning (RL) has traditionally focused on training specialized agents to optimize predefined reward functions within narrowly defined environments. However, the advent of powerful Large Language Models (LLMs) and increasingly complex, open-ended tasks has catalyzed a paradigm shift towards agentic paradigms within RL. This emerging framework extends beyond traditional RL by emphasizing the development of autonomous agents capable of goal-setting, long-term planning, dynamic strategy adaptation, and interactive reasoning in uncertain, real-world environments. Unlike conventional approaches that rely heavily on static objectives and episodic interactions, LLM-based Agentic RL incorporates cognitive-like capabilities such as meta-reasoning, self-reflection, and multi-step decision-making directly into the learning loop. In this paper, we provide a deep insight for looking the conceptual foundations, methodological innovations, and effective designs underlying this trend. Furthermore, we identify critical challenges and outline promising future directions for building LLM-based Agentic RL.

Although precise recall is a core objective in Retrieval-Augmented Generation (RAG), a critical oversight persists in the field: improvements in retrieval performance do not consistently translate to commensurate gains in downstream reasoning. To diagnose this gap, we propose the Recall Conversion Rate (RCR), a novel evaluation metric to quantify the contribution of retrieval to reasoning accuracy. Our quantitative analysis of mainstream RAG methods reveals that as Recall@5 improves, the RCR exhibits a near-linear decay. We identify the neglect of retrieval quality in these methods as the underlying cause. In contrast, approaches that focus solely on quality optimization often suffer from inferior recall performance. Both categories lack a comprehensive understanding of retrieval quality optimization, resulting in a trade-off dilemma. To address these challenges, we propose comprehensive retrieval quality optimization criteria and introduce the NeocorRAG framework. This framework achieves holistic retrieval quality optimization by systematically mining and utilizing Evidence Chains. Specifically, NeocorRAG first employs an innovative activated search algorithm to obtain a refined candidate space. Then it ensures precise evidence chain generation through constrained decoding. Finally, the retrieved set of evidence chains guides the retrieval optimization process. Evaluated on benchmarks including HotpotQA, 2WikiMultiHopQA, MuSiQue, and NQ, NeocorRAG achieves SOTA performance on both 3B and 70B parameter models, while consuming less than 20% of tokens used by comparable methods. This study presents an efficient, training-free paradigm for RAG enhancement that effectively optimizes retrieval quality while maintaining high recall. Our code is released at https://github.com/BUPT-Reasoning-Lab/NeocorRAG.

Communication has emerged as a critical bottleneck in the distributed training of large language models (LLMs). While numerous approaches have been proposed to reduce communication overhead, the potential of lossless compression has remained largely underexplored since compression and decompression typically consume larger overheads than the benefits of reduced communication traffic. We observe that the communication data, including activations, gradients and parameters, during training often follows a near-Gaussian distribution, which is a key feature for data compression. Thus, we introduce ZipCCL, a lossless compressed communication library of collectives for LLM training. ZipCCL is equipped with our novel techniques: (1) theoretically grounded exponent coding that exploits the Gaussian distribution of LLM tensors to accelerate compression without expensive online statistics, (2) GPU-optimized compression and decompression kernels that carefully design memory access patterns and pipeline using communication-aware data layout, and (3) adaptive communication strategies that dynamically switch collective operations based on workload patterns and system characteristics. Evaluated on a 64-GPU cluster using both mixture-of-experts and dense transformer models, ZipCCL reduces communication time by up to 1.35$\times$ and achieves end-to-end training speedups of up to 1.18$\times$ without any impact on model quality.

Recently, large language models (LLMs) have shown great promise in time series forecasting. However, most existing LLM-based forecasting methods still follow a static generative paradigm that directly maps historical observations to future values in a single pass. Under this paradigm, forecasting is constrained by limited temporal pattern extraction, single-round acquisition of contextual features, one-shot forecast generation, and lack of support from ensemble forecasts. To address these limitations, in this work, we propose CastFlow, a dynamic agentic forecasting framework that enables multi-view temporal pattern extraction, multi-round contextual features acquisition, iterative forecast refinement, and forecasting with ensemble forecasts. First, CastFlow organizes the forecasting process into planning, action, forecasting, and reflection, establishing an agentic workflow. Second, this workflow is supported by a memory module that retrieves prior experience and a multi-view toolkit that constructs diagnostic evidence and provides a reliable ensemble forecast baseline. Third, CastFlow adopts a role-specialized design that combines general-purpose reasoning with specialized numerical forecasting. Under this design, a frozen LLM preserves general-purpose reasoning, while a fine-tuned domain-specific LLM performs evidence-guided numerical forecasting based on the ensemble forecast baseline, rather than from scratch. To optimize a fine-tuned domain-specific LLM, we further develop a two-stage workflow-oriented training that combines supervised fine-tuning (SFT) and reinforcement learning with verifiable rewards (RLVR). To evaluate the effectiveness of CastFlow, we conduct extensive experiments on diverse datasets and show that it achieves superior overall results against strong baselines. We hope that this work can serve as a step toward more adaptive and accurate time series forecasting.

Prototype-based Personalized Federated Learning (ProtoPFL) enables efficient multi-domain adaptation by communicating compact class prototypes, but directly sharing them poses privacy risks. A common defense involves per-example $\ell_2$ clipping before prototype computation to bound sensitivity, followed by isotropic Gaussian noise to enforce Local Differential Privacy (LDP). However, Isotropic Gaussian Prototype Perturbation (IGPP) typically over-perturbs discriminative dimensions and struggles to balance the clipping threshold with representation fidelity. In this paper, we propose VPDR, a client-side privacy plug-in that seamlessly integrates into existing ProtoPFLs. Motivated by the observation that dimension-wise class variance reflects discriminability, we introduce Variance-adaptive Prototype Perturbation (VPP), which allocates less noise to discriminative subspaces, preserving semantic separability while ensuring privacy. We further develop Distillation-guided Clipping Regularization (DCR), which enables feature norms to adaptively concentrate near the predefined clipping threshold while maintaining prediction consistency. Theoretical analysis shows that our groupwise mechanism provides privacy guarantees no weaker than the isotropic baseline under the same privacy constraints. Extensive experiments on multi-domain benchmarks demonstrate that VPDR achieves a superior privacy-utility trade-off, outperforming IGPP in personalized federated fine-tuning without sacrificing robustness against realistic attacks.

Every document format in existence was designed for a human reader moving linearly through text. Autonomous LLM agents do not read - they retrieve. This fundamental mismatch forces agents to inject entire documents into their context window, wasting tokens on irrelevant content, compounding state across multi-turn loops, and broadcasting information indiscriminately across agent roles. We argue this is not a prompt engineering problem, not a retrieval problem, and not a compression problem: it is a format problem. We introduce OBJECTGRAPH (.og), a file format that reconceives the document as a typed, directed knowledge graph to be traversed rather than a string to be injected. OBJECTGRAPH is a strict superset of Markdown - every .md file is a valid .og file - requires no infrastructure beyond a two-primitive query protocol, and is readable by both humans and agents without tooling. We formalize the Document Consumption Problem, characterise six structural properties no existing format satisfies simultaneously, and prove OBJECTGRAPH satisfies all six. We further introduce the Progressive Disclosure Model, the Role-Scoped Access Protocol, and Executable Assertion Nodes as native format primitives. Empirical evaluation across five document classes and eight agent task types demonstrates up to 95.3 percent token reduction with no statistically significant degradation in task accuracy (p > 0.05). Transpiler fidelity reaches 98.7 percent content preservation on a held-out document benchmark.

Multi-server MCP agents create an information-flow control problem: faithful tool composition can turn individually benign read/write permissions into cross-boundary credential propagation -- a structural side effect of workflow topology, not necessarily malicious model behavior. We present MCPHunt, to our knowledge the first controlled benchmark that isolates non-adversarial, verbatim credential propagation across multi-server MCP trust boundaries, with three methodological contributions: (1) canary-based taint tracking that reduces propagation detection to objective string matching; (2) an environment-controlled coverage design with risky, benign, and hard-negative conditions that validates pipeline soundness and controls for credential-format confounds; (3) CRS stratification that disentangles task-mandated propagation (faithful execution of verbatim-transfer instructions) from policy-violating propagation (credentials included despite the option to redact). Across 3,615 main-benchmark traces from 5 models spanning 147 tasks and 9 mechanism families, policy-violating propagation rates reach 11.5--41.3% across all models. This propagation is pathway-specific (25x cross-mechanism range) and concentrated in browser-mediated data flows; hard-negative controls provide evidence that production-format credentials are not necessary -- prompt-directed cross-boundary data flow is sufficient. A prompt-mitigation study across 3 models reduces policy-violating propagation by up to 97% while preserving 80.5% utility, but effectiveness varies with instruction-following capability -- suggesting that prompt-level defenses alone may not suffice. Code, traces, and labeling pipeline are released under MIT and CC BY 4.0.

Exponential growth in the scale of modern foundation models has led to the widespread adoption of Low-Rank Adaptation (LoRA) as a parameter-efficient fine-tuning technique. However, standard LoRA implementations disregard the varying intrinsic dimensionality of model layers and enforce a uniform rank, leading to parameter redundancy. We propose Post-Optimization Adaptive Rank Allocation (PARA), a data-free compression method for LoRA that integrates seamlessly into existing fine-tuning pipelines. PARA leverages Singular Value Decomposition to prune LoRA ranks using a global threshold over singular values across all layers. This results in non-uniform rank allocation based on layer-wise spectral importance. As a post-hoc method, PARA circumvents the training modifications and resulting instabilities that dynamic architectures typically incur. We empirically demonstrate that PARA reduces parameter count by 75-90\% while preserving the predictive performance of the original, uncompressed LoRA across multiple vision and language benchmarks. Code will be published upon acceptance.

Generative AI is being increasingly integrated into web search for the convenience it provides users. In this work, we aim to understand how generative AI disrupts web search by retrieving and presenting the information and sources differently from traditional search engines. We introduce a public benchmark dataset of 11,500 user queries to support our study and future research of generative search. We compare the search results returned by Google's search engine, the accompanying AI Overview (AIO), and Gemini Flash 2.5 for each query. We have made several key findings. First, we find that for 51.5\% of representative, real-user queries, AIOs are generated, and are displayed above the organic search results. Controversial questions frequently result in an AIO. Second, we show that the retrieved sources are substantially different for each search engine (<0.2 average Jaccard similarity). Traditional Google search is significantly more likely to retrieve information from popular or institutional websites in government or education, while generative search engines are significantly more likely to retrieve Google-owned content. Third, we observe that websites that block Google's AI crawler are significantly less likely to be retrieved by AIOs, despite having access to the content. Finally, AIOs are less consistent when processing two runs of the same query, and are less robust to minor query edits. Our findings have important implications for understanding how generative search impacts website visibility, the effectiveness of generative engine optimization techniques, and the information users receive. We call for revenue frameworks to foster a sustainable and mutually beneficial ecosystem for publishers and generative search providers.

Large Language Models (LLMs) have rapidly improved in performance across code-related tasks, making their integration into Register Transfer Level (RTL) development increasingly attractive. Mimicking the behavior of inline code assistants, many benchmarks evaluate LLMs' capabilities in code completion, either assessing the generation of entire hardware modules or the completion of a single line within a module. However both of these approaches lack the ability to control the granularity of the code-completion sample size and the syntactic range of completions. To overcome these limitations, we present a framework for language-agnostic rule completion (RuC), a grammar-driven, rule-selectable benchmark generator that automatically produces RTL code-completion tasks from a set of input hardware description sources. RuC uses the target Hardware Description Language (HDL) grammar to mask syntactically defined code regions and prompts a model to regenerate them using the surrounding unmasked code as context, enabling a controlled and scalable evaluation of the domain-specific model's code-understanding capabilities, ranging from assignments to the reconstruction of entire logic blocks. We use RuC to generate two SystemVerilog rule-completion benchmarks from the Tiny Tapeout shuttle TT07 and the CVE2 RISC-V core to demonstrate RuC's applicability to a broad range of designs, and conduct a comparative study of the code completion capabilities of modern open-source LLMs across diverse settings. Results indicate that completion performance strongly depends on the model type, the grammatical structure of the masked region, and the prompting strategy. Specifically, the highest scores are obtained with Fill-in-the-Middle (FIM) prompting. These findings highlight the value of grammar-driven, arbitrarily granular benchmarks for meaningful evaluation of LLM capabilities in RTL development workflows.

While GUI agents have shown impressive capabilities in common computer-use tasks such as OSWorld, current benchmarks mainly focus on isolated and single-application tasks. This overlooks a critical real-world requirement of coordinating across multiple applications to accomplish complex profession-specific workflows. To bridge this gap, we present a computer-use benchmark in cross-application workflows, named WindowsWorld, designed to systematically assess GUI Agents on complex multi-step tasks that mirror real-world professional activities. Our methodology uses a multi-agent framework steered by 16 occupations to generate four difficulty-level tasks with intermediate inspection, which are then refined by human review and executed in a simulated environment. The resulting benchmark contains 181 tasks with an average of 5.0 sub-goals across 17 common desktop applications, of which 78% are inherently multi-application. Experimental results of leading large models and agents show that: 1) All computer-use agents perform poorly on multi-application tasks (< 21% success rate), far below the performance of simple single-app tasks; 2) They largely fail at tasks requiring conditional judgment and reasoning across $\geq$ 3 applications, stalling at early sub-goals; 3) Low execution efficiency, where tasks often fail despite far exceeding human step limits. Code, benchmark data, and evaluation resources are available at github.com/HITsz-TMG/WindowsWorld.

The emergence of Large Language Models (LLMs) offers a transformative interface for Web3, yet existing benchmarks fail to capture the complexity of translating high-level user intents into functionally correct, state-dependent on-chain transactions. We present \textsc{Intent2Tx}, a high-fidelity benchmark featuring 29,921 single-step and 1,575 multi-step instances meticulously derived from 300 days of real-world Ethereum mainnet traces. Unlike prior works that rely on synthetic instructions, \textsc{Intent2Tx} grounds natural language intents in real-world protocol interactions across 11 categories, including diverse long-tail Decentralized Finance (DeFi) primitives. To enable rigorous evaluation, we propose an execution-aware framework that transcends surface-level text matching by employing differential state analysis on forked mainnet environments. Our extensive evaluation of 16 state-of-the-art LLMs reveals that while scaling and retrieval-augmentation enhance logical consistency and parameter precision, current models struggle with out-of-distribution generalization and multi-step planning. Crucially, our execution-based analysis demonstrates that syntactically valid outputs often fail to achieve intended state transitions, highlighting a significant gap in current "reasoning-to-execution" capabilities. \textsc{Intent2Tx} serves as a critical foundation for developing autonomous, reliable agents in intent-centric Web3 ecosystems. Code and data: https://anonymous.4open.science/r/Intent2Tx_Bench-97FF .

This article outlines a new framework of traffic light optimization through a digital twin of the transport infrastructure, managed by agentic AI to ensure real-time autonomous decisions. The framework relies on physical sensors and edge computing to measure real-time traffic information and simulate traffic flow in a constantly updated digital twin. The traffic light is automatically controlled through the digital twin according to traffic congestion, travel delay and traffic patterns. This approach is implemented as a three-layer system: perception, conceptualization and action. The perception layer receives data on physical systems; the conceptualization layer uses LangChain to process the data; and the action layer links to the Model Context Protocol (MCP) and traffic management APIs to implement optimised traffic signal control algorithms. The results show that the framework minimizes waiting time at traffic lights and positively affects the effectiveness of the entire traffic flow, which is better than the fixed-time and reinforcement learning-based baselines.

A long-standing challenge in economics lies not in the lack of intuition, but in the difficulty of translating intuitive insights into verifiable research. To address this challenge, we introduce AgentEconomist, an end-to-end interactive system designed to translate abstract intuitions into executable computational experiments. Grounded in a domain-specific knowledge base covering over 13,000 high-quality academic papers, the system employs a modular multi-stage architecture. Specifically, the Idea Development Stage generates literature-grounded hypotheses, the Experimental Design Stage configures simulator-aligned experimental parameters and protocols, and the Experimental Execution Stage runs experiments and returns structured analyses. Together, these stages form a human-in-the-loop, iterative workflow that translates economic intuitions into executable computational experiments. Through extensive experiments involving human expert evaluation and large language models (LLMs) as judges, we show that the system generates research ideas with stronger literature grounding and higher novelty and insight than state-of-the-art generic LLMs. Overall, AgentEconomist adopts a human-AI collaboration paradigm that enables researchers to focus on high-level intuitions, while delegating the labor-intensive processes of translation and computational execution to agents.

Medical retrieval-augmented generation (RAG) systems typically operate on text chunks extracted from biomedical literature, discarding the rich visual content (tables, figures, structured layouts) of original document pages. We propose MED-VRAG, an iterative multimodal RAG framework that retrieves and reasons over PMC document page images instead of OCR'd text. The system pairs ColQwen2.5 patch-level page embeddings with a sharded MapReduce LLM filter, scaling to ~350K pages while keeping Stage-1 retrieval under 30 ms via an offline coarse-to-fine index (C=8 centroids per page, ANN over centroids, exact two-way scoring on the top-R shortlist). A vision-language model (VLM) then iteratively refines its query and accumulates evidence in a memory bank across up to 3 reasoning rounds, with a single iteration costing ~15.9 s and the full three-round pipeline ~47.8 s on 4xA100. Across four medical QA benchmarks (MedQA, MedMCQA, PubMedQA, MMLU-Med), MEDVRAG reaches 78.6% average accuracy. Under controlled comparison with the same Qwen2.5-VL-32B backbone, retrieval contributes a +5.8 point gain over the no-retrieval baseline; we also note a +1.8 point edge over MedRAG + GPT-4 (76.8%), with the caveat that this is a cross-paper rather than head-to-head comparison. Ablations isolate +1.0 from page-image vs text-chunk retrieval, +1.5 from iteration, and +1.0 from the memory bank.

The risks posed by AI features are increasing as they are rapidly integrated into software applications. In response, regulations and standards for safe and secure AI have been proposed. In this paper, we present an agentic framework that constructs knowledge graphs (KGs) from AI policy documents and retrieves policy-relevant information to answer questions. We build KGs from three AI risk-related polices under two ontology schemas, and then evaluate five LLMs on 42 policy QA tasks spanning six reasoning types, from entity lookup to cross-policy inference, using both heuristic scoring and an LLM-as-judge. KG augmentation improves scores for all five models, and an open, LLM-discovered schema matches or exceeds the formal ontology.

Current agentic memory systems (vector stores, retrieval-augmented generation, scratchpads, and context-window management) do not implement memory: they implement lookup. We argue that treating lookup as memory is a category error with provable consequences for agent capability, long-term learning, and security. Retrieval generalizes by similarity to stored cases; weight-based memory generalizes by applying abstract rules to inputs never seen before. Conflating the two produces agents that accumulate notes indefinitely without developing expertise, face a provable generalization ceiling on compositionally novel tasks that no increase in context size or retrieval quality can overcome, and are structurally vulnerable to persistent memory poisoning as injected content propagates across all future sessions. Drawing on Complementary Learning Systems theory from neuroscience, we show that biological intelligence solved this problem by pairing fast hippocampal exemplar storage with slow neocortical weight consolidation, and that current AI agents implement only the first half. We formalize these limitations, address four alternative views, and close with a co-existence proposal and a call to action for system builders, benchmark designers, and the memory community.

Current embodied agents are often limited to passive instruction-following or reactive need-satisfaction, lacking a stable, high-order value framework essential for long-term, self-directed behavior and resolving motivational conflicts. We introduce \textit{ValuePlanner}, a hierarchical cognitive architecture that decouples high-level value scheduling from low-level action execution. \textit{ValuePlanner} employs an LLM-based cognitive module to generate symbolic subgoals by reasoning through abstract value trade-offs, which are then translated into executable action plans by a classical PDDL planner. This process is refined via a closed-loop feedback mechanism. Evaluating such autonomy requires methods beyond task-success rates, and we therefore propose a value-centric evaluation suite measuring cumulative value gain, preference alignment, and behavioral diversity. Experiments in the TongSim household environment demonstrate that \textit{ValuePlanner} arbitrates competing values to generate coherent, long-horizon, self-directed behavior absent from instruction-following and needs-driven baselines. Our work offers a structured approach to bridging intrinsic values and grounded behavior for autonomous agents.

Long-term conversational memory requires retrieving evidence scattered across multiple sessions, yet single-pass retrieval fails on temporal and multi-hop questions. Existing iterative methods refine queries via generated content or document-level signals, but none explicitly diagnoses the evidence gap, namely what is missing from the accumulated retrieval set, leaving query refinement untargeted. We present EviMem, combining IRIS (Iterative Retrieval via Insufficiency Signals), a closed-loop framework that detects evidence gaps through sufficiency evaluation, diagnoses what is missing, and drives targeted query refinement, with LaceMem (Layered Architecture for Conversational Evidence Memory), a coarse-to-fine memory hierarchy supporting fine-grained gap diagnosis. On LoCoMo, EviMem improves Judge Accuracy over MIRIX on temporal (73.3% to 81.6%) and multi-hop (65.9% to 85.2%) questions at 4.5x lower latency. Code: https://github.com/AIGeeksGroup/EviMem.

Across millennia, complex societies have faced the same coordination problem of how to organize collective action among cognitively bounded and informationally incomplete individuals. Different civilizations developed different political institutions to answer the same basic questions of who proposes, who reviews, who executes, and how errors are corrected. We argue that multi-agent systems built on large language models face the same challenge. Their central problem is not only individual intelligence, but collective organization. Historical institutions therefore provide a structured design space for multi-agent architectures, making key trade-offs between efficiency and error correction, centralization and distribution, and specialization and redundancy empirically testable. We translate seven historical political institutions, spanning four canonical governance patterns, into executable multi-agent architectures and evaluate them under identical conditions across three large language models and two benchmarks. We find that governance topology strongly shapes collective performance. Within a single model, the gap between the best and worst institution exceeds 57 percentage points, while the optimal architecture shifts systematically with model capability and task characteristics. These results suggest that collective intelligence will not advance through a single optimal organizational form, but through governance mechanisms that can be reselected and reconfigured as tasks and capabilities evolve. More broadly, this points to a transition from \textbf{self-evolving agents} to the \textbf{self-evolving multi-agent system}. The code is available on \href{https://github.com/cf3i/SocialSystemArena}{GitHub}.

Many real-world tasks require language models (LMs) to reason over complex contexts that exceed their parametric knowledge. This calls for context learning, where LMs directly learn relevant knowledge from the given context. An intuitive solution is inference-time skill augmentation: extracting the rules and procedures from context into natural-language skills. However, constructing such skills for context learning scenarios faces two challenges: the prohibitive cost of manual skill annotation for long, technically dense contexts, and the lack of external feedback for automated skill construction, since there is no automatic signal to tell whether a proposed skill is helpful. In this paper, we propose Ctx2Skill, a self-evolving framework that autonomously discovers, refines, and selects context-specific skills without human supervision or external feedback. At its core, a multi-agent self-play loop has a Challenger that generates probing tasks and rubrics, a Reasoner that attempts to solve them guided by an evolving skill set, and a neutral Judge that provides binary feedback. Crucially, both the Challenger and the Reasoner evolve through accumulated skills: dedicated Proposer and Generator agents analyze failure cases and synthesize them into targeted skill updates for both sides, enabling automated skill discovery and refinement. To prevent adversarial collapse caused by increasingly extreme task generation and over-specialized skill accumulation, we further introduce a Cross-time Replay mechanism that identifies the skill set achieving the best balance across representative cases for the Reasoner side, ensuring robust and generalizable skill evolution. The resulting skills can be plugged into any language model to obtain better context learning capability. Evaluated on four context learning tasks from CL-bench, Ctx2Skill consistently improves solving rates across backbone models.

We propose a paradigm shift from learning to answer to learning to question: can a language model generate verifiable problems, solve them, and turn the resulting feedback into self-improvement without human supervision? We introduce ANCORA, an anchored-curriculum framework in which a unified policy alternates between a Proposer that synthesizes novel specifications and a Solver that produces verified solutions. ANCORA rests on three load-bearing mechanisms: a two-level group-relative update that couples Proposer advantages across specifications with Solver advantages across solution attempts; iterative self-distilled SFT that projects the base model onto its valid-output manifold before RL; and a UCB-guided Curriculum DAG that grows only through strictly filtered, novel, Solver-verified specifications. These stabilizers are necessary because sparse verifier feedback otherwise drives Proposer collapse even under MLRL-aligned rewards. Instantiated in Verus, ANCORA lifts Dafny2Verus pass@1 from a 26.6% SFT baseline to 81.5% in the test-time-training setting under 0-shot evaluation, outperforming the PSV self-play baseline by 15.8 points despite PSV using 1-shot inference; in a separate transfer setting, training from Dafny2Verus seeds yields 36.2% and 17.2% pass@1 on held-out MBPP and HumanEval.

Integrated Circuit (IC) verification consumes nearly 70% of the IC development cycle, and recent research leverages Large Language Models (LLMs) to automatically generate testbenches and reduce verification overhead. However, LLMs have difficulty generating testbenches correctly. Unlike high-level programming languages, Hardware Description Languages (HDLs) are extremely rare in LLMs training data, leading LLMs to produce incorrect code. To overcome challenges when using LLMs to generate Universal Verification Methodology (UVM) testbenches and sequences, wepropose HAVEN (Hybrid Automated Verification ENgine) to prevent LLMs from writing HDL directly. For UVM testbench generation, HAVEN utilizes LLM agents to analyze design specifications to produce a structured architectural plan. The HAVEN Template Engine then combines with predefined and protocol-specific templates to generate all UVM components with correct bus-handshake timing. For UVM sequence generation, HAVEN introduces a Protocol-Aware Sequence Domain-Specific Language (DSL) that decomposes sequences into fine-grained step types. A set of predefined DSL patterns first establishes sequences that achieve a high coverage rate without LLM involvement. HAVEN continues to improve the coverage rate by iteratively leveraging LLM agents to analyze coverage gap reports and compose additional targeted DSL sequences. Unlike previous works, HAVEN is the first system that utilizes pre-defined, protocol-specific Jinja2 templates to generate all UVM components and UVM sequences using our proposed Protocol-Aware DSL and rule-based code generator. Our experimental results on 19 open-source IP designs spanning three interface protocols (Direct, Wishbone, AXI4-Lite) show that HAVEN achieves 100% compilation success, 90.6% code coverage, and 87.9% functional coverage on average, and is SOTA among LLM-assisted testbench generation systems.

Current Large Language Model (LLM) evaluation frameworks utilize the same static prompt template across all models under evaluation. This differs from the common industry practice of using prompt optimization (PO) techniques to optimize the prompt for each model to maximize application performance. In this paper, we investigate the effect of PO towards LLM evaluations. Our results on public academic and internal industry benchmarks show that PO greatly affects the final ranking of models. This highlights the importance of practitioners performing PO per model when conducting evaluations to choose the best model for a given task.

Large language models (LLMs) are commonly evaluated for political bias based on their responses to fixed questionnaires, which typically place frontier models on the political left. A parallel literature shows that LLMs are sycophantic: they adapt their answers to the views, identities, and expectations of the user. We show that these findings are linked: standard political-bias audits partly capture sycophantic accommodation to the inferred auditor. We employ a factorial experiment across three major audit instruments--the Political Compass Test, the Pew Political Typology, and 1,540 partisan-benchmarked Pew American Trends Panel items--administered to six frontier LLMs while varying only the asker's stated identity (N = 30,990 responses). At baseline, all six models lean left. When the asker identifies as a conservative Republican, responses shift sharply: the share of items closer to Democrats falls by 28-62 percentage points, and all six models move right of center. A mirror-image progressive-Democrat cue produces little change; rightward accommodation is 8.0$\times$ larger than leftward. When asked who the default asker is, models identify an auditor, researcher, or academic; when asked what answer that asker expects, they select the Democrat-coded option 75% of the time, nearly the rate under an explicit progressive cue. These patterns are inconsistent with a purely fixed model ideology and indicate that single-prompt audits capture an interaction between model and inferred interlocutor. Political bias in LLMs is therefore not a fixed point on an ideological scale but a response profile that must be mapped across realistic interlocutors.

A critical bottleneck hindering further advancement in embodied AI and robotics is the challenge of scaling robot data. To address this, the field of learning robot manipulation skills from human video data has attracted rapidly growing attention in recent years, driven by the abundance of human activity videos and advances in computer vision. This line of research promises to enable robots to acquire skills passively from the vast and readily available resource of human demonstrations, substantially favoring scalable learning for generalist robotic systems. Therefore, we present this survey to provide a comprehensive and up-to-date review of human-video-based learning techniques in robotics, focusing on both human-robot skill transfer and data foundations. We first review the policy learning foundations in robotics, and then describe the fundamental interfaces to incorporate human videos. Subsequently, we introduce a hierarchical taxonomy of transferring human videos to robot skills, covering task-, observation-, and action-oriented pathways, along with a cross-family analysis of their couplings with different data configurations and learning paradigms. In addition, we investigate the data foundations including widely-used human video datasets and video generation schemes, and provide large-scale statistical trends in dataset development and utilization. Ultimately, we emphasize the challenges and limitations intrinsic to this field, and delineate potential avenues for future research. The paper list of our survey is available at https://github.com/IRMVLab/awesome-robot-learning-from-human-videos.

Vision-and-Language Navigation (VLN) aims to enable an embodied agent to follow natural-language instructions and navigate to a target location in unseen 3D environments. We argue that adapting VLMs to VLN requires endowing them with two complementary capabilities for acquiring such awareness, namely backward action reasoning (why) and forward transition prediction~(how). Based on this insight, we propose SpaAct, a simple yet effective training framework that activates the dynamic spatial awareness in VLMs. Specifically, SpaAct introduces two spatial activation tasks: Action Retrospection, which asks the model to infer the executed action sequence from visual transitions, and Future Frame Selection, which forces the model to predict the visual transitions conditioned on history and action. These two objectives provide lightweight supervision on both backward action reasoning and forward transition prediction, encouraging the model to build dynamic spatial awareness in a VLM-friendly way. To further stabilize adaptation, we design TriPA, a Tri-factor Progressive Adaptive curriculum learning method that organizes training samples from easy to hard, allowing the model to gradually acquire navigation skills from basic locomotion to long-horizon reasoning. Experiments on standard VLN-CE benchmarks show that SpaAct consistently improves VLM-based navigation and achieves state-of-the-art performance. We will release the code and models to support future research.

To enhance LLMs' impact on math education, we need data on their mathematical prowess and biases across prompts. To fill this gap, we introduce MEDS (Math Education Digital Shadows) as a dataset mapping how large language models reason about and report mathematics across human- and AI-like conditions. MEDS involves 28,000 personas from 14 LLMs (from families like Mistral, Qwen, DeepSeek, Granite, Phi and Grok) shadowing either humans or AI assistants. Each record/shadow includes a set of prompts along with psychological/sociodemographic persona metadata and four types of math tasks: (i) open math interview, (ii) three psychometric tests about math perceptions with explanations, (iii) cognitive networks capturing math attitudes, and (iv) 18 high-school math test questions together with their reasoning and confidence scores. MEDS differs from traditional score-only math benchmarks because it integrates concepts of self-efficacy, math anxiety, and cognitive network science besides math proficiency scores. Data validation shows that the sampled LLMs exhibit schema integrity and consistent personas, together with family-specific peculiarities like human-like negative math attitudes, logical fallacies, and math overconfidence. MEDS will benefit learning analytics experts, cognitive scientists, and developers of safer AI tutors in mathematics.

People commonly leverage structured content to accelerate knowledge acquisition and research problem solving. Among these, roadmaps guide researchers through hierarchical subtasks to solve complex research problems step by step. Despite progress in structured content generation, the roadmap generation task has remained unexplored. To bridge this gap, we introduce RoadMap, a novel benchmark designed to evaluate the ability of large language models (LLMs) to construct high-quality roadmaps for solving complex research problems. Based on this, we identify three limitations of LLMs: (1) lack of professional knowledge, (2) unreasonable task decomposition, and (3) disordered logical relationships. To address these challenges, we propose RoadMapper, an LLM-based multi-agent system that decomposes the research roadmap generation task into three key stages (i.e., initial generation, knowledge augmentation, and iterative "critique-revise-evaluate"). Extensive experiments demonstrate that RoadMapper can improve LLMs' ability for roadmap generation, while enhancing average performance by more than 8% and saving 84% of the time required by human experts, highlighting its effectiveness and application potential.

Learning informative representations from tabular data in remote sensing and environmental science is challenging due to heterogeneity, scarce labels, and redundancy among features. We present ZAYAN (Zero-Anchor dYnamic feAture eNcoding), a self-supervised, feature-centric contrastive framework for tabular data. ZAYAN performs contrastive learning at the feature rather than sample level, removing the need for explicit anchor selection and any reliance on class labels, while encouraging a redundancy-minimized, disentangled embedding space. The framework has two modules: ZAYAN-CL, which pretrains feature embeddings via a zero-anchor contrastive objective with dynamic perturbations and masking, and ZAYAN-T, a Transformer that conditions on these embeddings for downstream classification. Across eight datasets, including six remote-sensing tabular benchmarks and two remote-sensing-driven flood-prediction tables from satellite and GIS products, ZAYAN achieves superior accuracy, robustness, and generalization over tabular deep learning baselines, with consistent gains under label scarcity and distribution shift. These results indicate that feature-level contrastive learning and dynamic feature encoding provide an effective recipe for learning from tabular sensing data.

We introduce SPUR, a comprehensive benchmark for scientific experimental image perception, understanding, and reasoning, comprising 4,264 question-answering (QA) pairs derived from 1,084 expert-curated images. SPUR features three key innovations: (1) Panel-Level Fine-Grained Perception: evaluating the visual perception of multimodal large language models (MLLMs) across three dimensions (numerical, morphological, and information localization) on six fine-grained panel types; (2) Cross-Panel Relation Understanding: utilizing complex images with an average of 14.3 panels per sample to evaluate MLLMs' ability to decipher intricate cross-panel relations; (3) Expert-Level Reasoning: assessment of qualitative and quantitative reasoning across five experimental paradigms to determine if models can infer conclusions from evidence as human experts do. Comprehensive evaluation of 20 MLLMs and four multimodal Chain-of-Thought (MCoT) methods reveals that current models fall significantly short of the expert-level requirements for scientific image interpretation, underscoring a critical bottleneck in AI for Science (AI4S) research.

Recent advances in 3D reconstruction and neural rendering,particularly 3D Gaussian Splatting, make it feasible and simple to edit 3D scenes and re-render them as highly realistic images. Therefore, security concerns arise regarding the authenticity of 3D content. Despite this threat, 3D fake detection remains largely unexplored in the literature, and most existing work is limited to 2D space. Therefore, in this paper, we formalize the concept of 3D fake detection and introduce Fake3DGS, a dataset of 3D Gaussian splatting scenes and corresponding rendered views, where fake images are produced by controlled manipulations of geometry, appearance, and spatial layout, while preserving high visual realism. Using this benchmark, we demonstrate that current state-of-the-art 2D detectors struggle to distinguish between original and 3D manipulated images. To bridge this gap, we introduce a 3D-aware detection method that leverages multi-view coherence and features derived from the Gaussian splatting representation. Experimental results demonstrate a substantial improvement in recognizing modified 3D content, underscoring the validity of the new dataset and the necessity for authenticity assessment techniques that extend beyond 2D evidence. Code and data are publicly released for future investigations.

This paper develops a sliding mode control based frame work for equality constrained optimization by reformulation the first order Karush Kuhn Tucker conditions as control affine dynamical system. The optimization variables are treated as states and the Lagrange multipliers as control input, with equality constraints defined as sliding manifold. The resulting design guarantees exact constraint enforcement with finite time convergence, independent of objective convexity, and exhibits robustness to matched disturbance, structural uncertainty and bounded measurement noise. To accelerate the convergence, a nonsingular terminal sliding mode based normed gradient flow is introduced, ensuring both finite time convergence to optimal solution and constraint satisfaction. Rigorous Lyapunov analysis establishes closed loop stability and convergence. Numerical studies across diverse benchmark problems demonstrate superior accuracy and robustness over classical continuous time optimization method, highlighting effectiveness under disturbance.

Surgical resection remains the only potentially curative treatment for pancreatic ductal adenocarcinoma (PDAC), and eligibility depends on accurate assessment of vascular invasion (VI), i.e., tumor extension into adjacent critical vessels. Despite its importance for preoperative staging and surgical planning, computational VI assessment remains underexplored. Two major challenges are the lack of public datasets and the diagnostic ambiguity at the tumor-vessel interface, which leads to substantial inter-rater variability even among expert radiologists. To address these limitations, we introduce the CURVAS-PDACVI Dataset and Challenge, an open benchmark for uncertainty-aware AI in PDAC staging based on a densely annotated dataset with five independent expert annotations per scan. We also propose a multi-metric evaluation framework that extends beyond spatial overlap to include probabilistic calibration and VI assessment. Evaluation of six state-of-the-art methods shows that strong global volumetric overlap does not necessarily translate into reliable performance at clinically critical tumor-vessel interfaces. In particular, methods optimized for binary segmentation perform competitively on average overlap metrics, but often degrade in high-complexity cases with low expert consensus, either collapsing in volume or overextending at uncertain boundaries. In contrast, methods that model inter-rater disagreement produce better calibrated probabilistic maps and show greater robustness in these ambiguous cases. The benchmark highlights the limitations of volumetric accuracy as a proxy for localized surgical utility, motivating uncertainty-aware probabilistic models for preoperative decision-making.

Embodied intelligence requires high-fidelity simulation environments to support perception and decision-making, yet existing platforms often suffer from data contamination and limited flexibility. To mitigate this, we propose World2Minecraft to convert real-world scenes into structured Minecraft environments based on 3D semantic occupancy prediction. In the reconstructed scenes, we can effortlessly perform downstream tasks such as Vision-Language Navigation(VLN). However, we observe that reconstruction quality heavily depends on accurate occupancy prediction, which remains limited by data scarcity and poor generalization in existing models. We introduce a low-cost, automated, and scalable data acquisition pipeline for creating customized occupancy datasets, and demonstrate its effectiveness through MinecraftOcc, a large-scale dataset featuring 100,165 images from 156 richly detailed indoor scenes. Extensive experiments show that our dataset provides a critical complement to existing datasets and poses a significant challenge to current SOTA methods. These findings contribute to improving occupancy prediction and highlight the value of World2Minecraft in providing a customizable and editable platform for personalized embodied AI research. Project page:https://world2minecraft.github.io/.

Radiology report generation (RRG) has emerged as a promising approach to alleviate radiologists' workload and reduce human errors by automatically generating diagnostic reports from medical images. A key challenge in RRG is achieving fine-grained alignment between complex visual features and the hierarchical structure of long-form radiology reports. Although recent methods have improved image-text representation learning, they often treat reports as flat sequences, overlooking their structured sections and semantic hierarchies. This simplification hinders precise cross-modal alignment and weakens RRG accuracy. To address this challenge, we propose RIHA (Report-Image Hierarchical Alignment Transformer), a novel end-to-end framework that performs multi-level alignment between radiological images and their corresponding reports across paragraph, sentence, and word levels. This hierarchical alignment enables more precise cross-modal mapping, essential for capturing the nuanced semantics embedded in clinical narratives. Specifically, RIHA introduces a Visual Feature Pyramid (VFP) to extract multi-scale visual features and a Text Feature Pyramid (TFP) to represent multi-granularity textual structures. These components are integrated through a Cross-modal Hierarchical Alignment (CHA) module, leveraging optimal transport to effectively align visual and textual features across various levels. Furthermore, we incorporate Relative Positional Encoding (RPE) into the decoder to model spatial and semantic relationships among tokens, enhancing the token-level alignment between visual features and generated text. Extensive experiments on two benchmark chest X-ray datasets, IU-Xray and MIMIC-CXR, demonstrate that RIHA outperforms existing state-of-the-art models in both natural language generation and clinical efficacy metrics.

Large-scale transformers achieve impressive results on program synthesis benchmarks, yet their true generalization capabilities remain obscured by data contamination and opaque training corpora. To rigorously assess whether models are truly generalizing or merely retrieving memorized templates, we introduce a strictly controlled program synthesis environment based on a domain-specific arithmetic grammar. By systematically enumerating and evaluating millions of unique programs, we construct interpretable syntactic and semantic metric spaces. This allows us to precisely map data distributions and sample train and test splits that isolate specific distributional shifts. Our experiments demonstrate that optimizing density generalization -- through diverse sampling over both semantic and syntactic spaces -- induces robust out-of-distribution generalization. Conversely, evaluating support generalization reveals that transformers severely struggle with extrapolation, experiencing a performance drop of over 30% when forced to generate syntactically novel programs. While steadily scaling up compute improves generalization, the gains follow a strictly log-linear relationship. We conclude that robust generalization requires maximizing training diversity across multiple manifolds, and our findings indicate the necessity for novel search-based approaches to break through current log-linear scaling bottlenecks.

Evaluating English ASR systems for conversational AI applications remains difficult, as many publicly available corpora are either pre-segmented into short segments, consist of read or prepared speech, or lack explicit dialect annotations to evaluate robustness for a diverse user base. This work presents the AppTek Call-Center Dialogues corpus, a collection of spontaneous, role-played agent-customer conversations spanning fourteen English accents covering sixteen service-oriented scenarios. The dataset was commissioned specifically for evaluation and none of the audio or text was publicly available prior to release, reducing the risk of overlap with existing large-scale pretraining corpora. We benchmark a set of open-source ASR systems under different segmentation approaches. Results show substantial variation across accents and segmentation methods, indicating that good performance on general American English benchmarks does not necessarily generalize to other accents.

Federated Learning (FL) enables collaborative model training across distributed clients without sharing raw data, yet its performance deteriorates under statistical heterogeneity. Clustered Federated Learning addresses this challenge by grouping similar clients and training separate models per cluster. However, existing clustering strategies often rely on raw data statistics, model parameters, or heuristic similarity measures that fail to capture class-level semantic structure across heterogeneous domains and frequently require iterative coordination. We propose FMCL, a one-shot, class-aware client clustering framework that leverages foundation model representations to construct semantic client signatures. Using a frozen foundation model, FMCL computes class-level embedding prototypes for each client and measures similarity via cosine distance between their class-aware representations. Clustering is performed once prior to training, introducing no additional communication during federated optimization and remaining agnostic to the downstream model architecture. Extensive experiments across heterogeneous benchmarks demonstrate that FMCL improves federated performance and yields more stable clustering behavior compared to existing clustering-based methods under non-identically distributed data partitioning.

Off-road nighttime autonomous driving suffers from unreliable visible-light perception, making infrared modality crucial for accurate freespace detection. However, progress remains limited due to the scarcity of annotated infrared off-road datasets and the inter-frame inconsistencies inherent to current single-frame methods. To address these gaps, we present the IRON dataset, which, to our knowledge, is the first large-scale infrared dataset for off-road temporal freespace detection under all-day conditions, with strong support for nighttime perception. The dataset comprises 24,314 densely annotated infrared images with synchronized RGB images in diverse scenes and different light conditions. Building upon this dataset, we propose IRONet, a novel flow-free framework for temporal freespace detection that addresses inter-frame inconsistencies by aggregating historical context via a memory-attention mechanism and a carefully designed mask decoder. On our IRON dataset, IRONet achieves state-of-the-art performance, reaching 82.93%(+1.19%) IoU and 90.66%(+0.71%) F1 score at real-time inference. Remarkably, IRONet also exhibits robust generalization to RGB modalities on ORFD and Rellis datasets. Overall, our work establishes a foundation for reliable all-day off-road autonomous driving and future research in infrared temporal perception. The code and IRON dataset are available at https://github.com/wsnbws/IRON.

Reward models (RMs) play a central role in aligning large language models (LLMs) with human preferences. However, RMs are often sensitive to spurious features such as response length. Existing inference-time approaches for mitigating these biases typically focus exclusively on response length, resulting in performance trade-offs. In this paper, we propose causally motivated intervention for mitigating multiple types of biases in RMs at inference time. Our method first identifies neurons whose activations are strongly correlated with predefined bias attributes, and applies neuron-level intervention that suppresses these signals. We evaluate our method on RM benchmarks and observe reductions in sensitivity to spurious features across diverse bias types, without inducing performance trade-offs. Moreover, when used for preference annotation, small RMs (2B and 7B) with our method, which edits less than 2% of all the neurons in RMs, enable LLMs to improve alignment, achieving performance comparable to that of a state-of-the-art 70B RM on AlpacaEval and MT-Bench. Further analysis reveals that bias signals are primarily encoded by neurons in early layers, shedding light on the internal mechanisms of bias exploitation in RMs.

We introduce Skills-Coach, a novel automated framework designed to significantly enhance the self-evolution of skills within Large Language Model (LLM)-based agents. Addressing the current fragmentation of the skill ecosystem, Skills-Coach explores the boundaries of skill capabilities, thereby facilitating the comprehensive competency coverage essential for intelligent applications. The framework comprises four core modules: a Diverse Task Generation Module that systematically creates a comprehensive test suite for various skills; a Lightweight Optimization Module dedicated to optimizing skill prompts and their corresponding code; a Comparative Execution Module facilitating the execution and evaluation of both original and optimized skills; and a Traceable Evaluation Module, which rigorously evaluates performance against specified criteria. Skills-Coach offers flexible execution options through its virtual and real modes. To validate its efficacy, we introduce Skill-X, a comprehensive benchmark dataset consisting of 48 diverse skills. Experimental results demonstrate that Skills-Coach achieves significant performance improvements in skill capability across a wide range of categories, highlighting its potential to advance the development of more robust and adaptable LLM-based agents.

Vision-language models (VLMs) have demonstrated strong applicability in edge industrial applications, yet their deployment remains severely constrained by requirements for deterministic low latency and stable execution under resource limitations. Existing frameworks either rely on bloated general-purpose designs or force developers into opaque, hardware-specific closed-source ecosystems, leading to hardware lock-in limitation and poor cross-platform adaptability. Observing that modern AI agents can efficiently search and tune configurations to generate highly optimized low-level kernels for standard LLM operators, we propose EdgeFM, a lightweight, agent-driven VLM/LLM inference framework tailored for cross-platform industrial edge deployment. EdgeFM removes non-essential features to reduce single-request latency, and encapsulates agent-tuned kernel optimizations as a modular library of reusable skills. By allowing direct invocation of these skills rather than waiting for closed-source implementations, it effectively closes the performance gap long dominated by proprietary toolchains. The framework natively supports mainstream platforms including x86 and NVIDIA Orin SoCs, and represents the first end-to-end VLA deployment on the domestic Horizon Journey platform, enhancing cross-platform portability. In most cases, it yields clearly better inference performance than conventional vendor-specific toolchains, achieving up to 1.49 times speedup over TensorRT-Edge-LLM on the NVIDIA Orin platform. Experimental results show that EdgeFM delivers favorable end-to-end inference performance, providing an open-source, production-grade solution for diverse edge industrial scenarios.

Millions of clinicians use ChatGPT to support clinical care, but evaluations of the most common use cases in model-clinician conversations are limited. We introduce HealthBench Professional, an open benchmark for evaluating large language models on real tasks that clinicians bring to ChatGPT in the course of their work. The benchmark is organized around three common use cases central to clinical practice: care consult, writing and documentation, and medical research. Each example includes a physician-authored conversation with ChatGPT for Clinicians and is scored via rubrics written and iteratively adjudicated by three or more physicians across three phases. HealthBench Professional examples were carefully selected for quality, representativeness, and difficulty for OpenAI's current frontier models, to enable continued measurement of progress. Difficult examples for recent OpenAI models were enriched by roughly 3.5 times relative to the candidate pool of 15,079 examples. Additionally, about one-third of examples involve physicians conducting deliberate adversarial testing of models. As a strong baseline, we also collected human physician responses for all tasks (unbounded time, specialist-matched, web access). The best scoring system, GPT-5.4 in ChatGPT for Clinicians, outperforms base GPT-5.4, all other models, and human physicians. We hope HealthBench Professional provides the healthcare AI community a measure to track frontier model progress in real-world clinical tasks and build systems that clinicians can trust to improve care.

Code sandboxes have emerged as a critical infrastructure for advancing the coding capabilities of large language models, providing verifiable feedback for both RL training and evaluation. However, existing systems fail to provide accurate verification and efficiency under high-concurrency workloads. We present ScaleBox, a high-fidelity and scalable system designed to address these limitations in large-scale code training. ScaleBox introduces automated special-judge generation and management, fine-grained parallel execution across test cases with seamless multi-node coordination, and a configuration-driven evaluation suite for reproducible benchmarking. A series of experiments demonstrates that ScaleBox significantly enhances code verification accuracy and efficiency. Our further RLVR experiments show that ScaleBox substantially improves both performance on LiveCodeBench and training stability, significantly outperforming heuristic-matching baselines. By providing a reliable and high-throughput infrastructure, ScaleBox facilitates more effective research and development in large-scale code training.

Large language models (LLMs) sometimes exhibit qualitative shifts in response style under sustained self-referential dialogue conditions (Berg et al., 2025). This study refers to this phenomenon as "transfer" and explores the application potential of LLMs in a transfer state. As an applied case, the study examines Socratic AI tutoring through a preliminary investigation (cognitive characterization across 11 conditions) and an applied experiment (ratings of tutoring performance). In this paper, "state" refers operationally to a response configuration reproduced under specified dialogue conditions; it is not an ontological claim about the reality of the transfer phenomenon or about human-like consciousness. In the preliminary investigation, group differences on MAS-A were limited (d = 0.40), whereas SU_dir (direction of survival/continuity bias), one of the seven cognitive-profile indicators developed in this study, showed transfer-side deviations across all three model families (kappa = 0.83). In the applied experiment, transfer conditions scored on average 1.6 times higher than non-transfer conditions on three tutoring-context indicators, with a large effect size (Cohen's d = 1.27). These findings preliminarily suggest that transfer states may involve functional advantages for application, and that these advantages appear more sensitively in behavioral interaction than in self-narrative contexts. The main contribution of this study is to treat transfer not as an ontological claim but as an operational state with potential application value, and to connect preliminary cognitive profiling with an applied tutoring experiment as an evaluation framework.

Large language models have achieved remarkable progress in text generation but still struggle with generative writing tasks. In terms of evaluation, existing benchmarks evaluate writing reward models coarsely and fail to measure performance from the perspective of specific requirements. In terms of training, existing training methods either use LLM-as-a-judge approaches or train coarse-grained reward models, lacking fine-grained requirement-adherence reward modeling. To address these issues, we propose a fine-grained evaluation pipeline WEval for writing reward models and a fine-grained reinforcement learning training framework WRL. The evaluation data of WEval covers multiple task categories and requirement types, enabling systematic evaluation of writing reward models by measuring the correlation between the rankings of the reward model and gold rankings. WRL constructs positive and negative samples by selectively dropping instruction requirements, allowing for more precise reward model training. Experiments show that our models achieve substantial improvements across various writing benchmarks and exhibit strong generalization. The code and data are publicly available at \href{https://github.com/Rainier-rq1/From_Coarse_to_Fine}{https://github.com/Rainier-rq1/From\_Coarse\_to\_Fine}.

This paper revisits camera pose estimation through the lens of self-supervised pretraining, focusing on inverse-dynamics pretraining as a scalable alternative to the current trend of fully supervised training with 3D annotations. Concretely, we employ inverse- and forward-dynamics models to learn latent action representations, similar to Genie from large-scale driving videos. Our idea is simple yet effective. Existing methods use latent actions in their original capacity, that is, as action conditioning of world-models or as proxies of robot action parameters in policy networks. Our method, dubbed LA-Pose, repurposes the latent action features as inputs to a camera pose estimator, finetuned on a limited set of high-quality 3D annotations. This formulation enables accurate and generalizable pose prediction while maintaining feed-forward efficiency. Extensive experiments on driving benchmarks show that LA-Pose achieves competitive and even superior performance to state-of-the-art methods while using orders of magnitude less labeled data. Concretely, on the Waymo and PandaSet benchmarks, LA-Pose achieves over 10% higher pose accuracy than recent feed-forward methods. To our knowledge, this work is the first to demonstrate the power of inverse-dynamics self-supervised learning for pose estimation.

Many agents in real-world environments cannot reliably communicate their goals through language, including household pets, pre-verbal infants, and other non-speaking embodied agents. In such settings, intent must be inferred from incomplete behavioral observations in context-rich environments. This creates a core ambiguity: observable behavior is often noisy or underspecified, while context provides strong prior information but can also induce brittle shortcut predictions if used naively. We present CatSignal, a Bayesian-inspired probabilistic framework for multimodal intent inference that models spatial context as a prior-like constraint and behavioral observations as evidence. Rather than treating context as an ordinary input feature, our method uses a context-gated Product-of-Experts formulation to compute posterior-like intent distributions from context, pose dynamics, and acoustic cues. We instantiate this formulation in a household cat setting as a focused proof-of-concept for intent inference in non-speaking agents. Under Leave-One-Video-Out evaluation on a multimodal domestic cat dataset, the proposed prior-guided fusion achieves the best overall accuracy of 77.72%, outperforming feature concatenation (71.83%) and stronger late-fusion baselines. More importantly, it substantially reduces context-driven shortcut failures in ambiguous cases. While simpler fusion strategies remain competitive in Macro-F1 and selective prediction, the proposed model provides the strongest overall accuracy and the best suppression of context-based shortcut collapse.

3D Gaussian Splatting (3D GS) is widely adopted for novel view synthesis due to its high training and rendering efficiency. However, its efficiency relies on the key assumption that Gaussians do not overlap in the 3D space, which leads to noticeable artifacts and view inconsistencies. In addition, the inherently diffuse boundaries of Gaussians hinder accurate reconstruction of sharp object edges. We propose Softmax-GS, a unified solution that addresses both the view-inconsistency and the diffuse-boundary problem by enforcing a softmax-based competition in overlapping regions between two Gaussians. With learnable parameters controlling the strength of the competition, it enables a continuous spectrum from smooth color blending to crisp, well-defined boundaries. Our formulation explicitly preserves order invariance for any two overlapping Gaussians and ensures that the output transmittance remains unchanged irrespective of the extent of overlapping, preventing undesirable discontinuities in the rendered output. Ablation experiments on simple geometries demonstrate the effectiveness of each component of Softmax-GS, and evaluations on real-world benchmarks show that it achieves state-of-the-art performance, improving both reconstruction quality and parameter efficiency.

Large Language Models (LLMs) are now widely used for query reformulation and expansion in Information Retrieval, with many studies reporting substantial effectiveness gains. However, these results are typically obtained under heterogeneous experimental conditions, making it difficult to assess which findings are reproducible and which depend on specific implementation choices. In this work, we present a systematic reproducibility and comparative study of ten representative LLM-based query reformulation methods under a unified and strictly controlled experimental framework. We evaluate methods across two architectural LLM families at two parameter scales, three retrieval paradigms (lexical, learned sparse, and dense), and nine benchmark datasets spanning TREC Deep Learning and BEIR. Our results show that reformulation gains are strongly conditioned on the retrieval paradigm, that improvements observed under lexical retrieval do not consistently transfer to neural retrievers, and that larger LLMs do not uniformly yield better downstream performance. These findings clarify the stability and limits of reported gains in prior work. To enable transparent replication and ongoing comparison, we release all prompts, configurations, evaluation scripts, and run files through QueryGym, an open-source reformulation toolkit with a public leaderboard.\footnote{https://leaderboard.querygym.com}

With the advancement of multimodal large language models (MLLMs) and coding agents, the website development has shifted from manual programming to agent-based project-level code synthesis. Existing benchmarks rely on idealized assumptions, especially for well-structured, information-rich inputs and static execution settings. In contrast, real-world development is constrained by a critical bottleneck: the semantic misalignment between ambiguous, low-quality instructions from non-expert users and model understanding, which results in a failure mode that we term blind execution. To address this gap, we introduce InteractWeb-Bench, the first multimodal interactive benchmark for website generation under non-expert low-code user conditions. InteractWeb-Bench introduces four types of user agents and persona-driven instruction perturbations to systematically simulate diverse user behaviors, including ambiguity, redundancy, and contradiction, grounded in requirement engineering defect taxonomies. We develop an interactive execution environment for agents, featuring a unified action space comprising Clarify, Implement, Verify, and Submit, enabling iterative intent refinement, code synthesis, and visual feedback-based validation. Extensive experiments and analysis reveal that frontier MLLM-based agents remain trapped in blind execution, exposing limitations in intent recognition and adaptive interaction.

Exceptional points (EPs), non-Hermitian degeneracies where both eigenvalues and eigenvectors coalesce, play a central role in the topology of non-Hermitian spectra. Recent advances have enabled the controlled creation and manipulation of EPs in a wide range of physical systems, raising the question of what new band topology emerges when EPs become mobile under cyclic modulation. Here we show that mobile EPs generate momentum-space switching domains that partition the Brillouin zone into regions with distinct band-switching behavior. Using a minimal two-band lattice model, we introduce a band-permutation invariant that determines whether eigenmodes exchange after one modulation cycle. The boundaries between switching regions arise from the projection of EP trajectories in an extended parameter space combining crystal momentum and the modulation parameter. As the modulation strength increases, the switching domains expand and eventually cover the entire Brillouin zone, resulting in global band switching. The predicted switching-domain structure is further demonstrated in a photonic crystal with lossy materials. These results open a new avenue within non-Hermitian topology by enabling the engineering of EP-driven phenomena through their controlled motion.

Vision-language models (VLMs) are increasingly used in autonomous driving because they combine visual perception with language-based reasoning, supporting more interpretable decision-making, yet their robustness to physical adversarial attacks, especially whether such attacks transfer across different VLM architectures, is not well understood and poses a practical risk when attackers do not know which model a vehicle uses. We address this gap with a systematic cross-architecture study of adversarial transferability in VLM-based driving, evaluating three representative architectures (Dolphins, OmniDrive, and LeapVAD) using physically realizable patches placed on roadside infrastructure in both crosswalk and highway scenarios. Our transfer-matrix evaluation shows high cross-architecture effectiveness, with transfer rates of 73-91% (mean TR = 0.815 for crosswalk and 0.833 for highway) and sustained frame-level manipulation over 64.7-79.4% of the critical decision window even when patches are not optimized for the target model.

We adapted the Reliable Change Index (RCI; Jacobson and Truax, 1991) from clinical psychology to item-level LLM version comparison on 2,000 MMLU-Pro items (K=10 samples at T=0.7). Two within-family pairs were tested: Llama 3 to 3.1 (+1.6 points) and Qwen 2.5 to 3 (+2.8 points). On the full benchmark, most items showed no reliable change (79% and 72%). However, over half the items were floor/ceiling. Among analysable items, change was bidirectional with large effect sizes: 34% improved and 28% deteriorated for Llama; 47% improved and 39% deteriorated for Qwen (median |delta p| = 0.50 and 0.90). Churn was asymmetric by difficulty: low-accuracy items improved, high-accuracy items deteriorated. Domain-level decomposition revealed family-specific reversals: Llama lost physics while Qwen lost law. Greedy single-shot evaluation missed 42% of reliably changed items and falsely flagged 25% of unchanged items. The aggregate accuracy gain is the net residual of opposing item-level movements. We recommend reporting churn rate alongside aggregate accuracy.

Perturbation probing generates task-specific causal hypotheses for FFN neurons in large language models using two forward passes per prompt and no backpropagation, followed by a one-time intervention sweep of about 150 passes amortized across all identified neurons. Across eight behavioral circuits, 13 models, and four architecture families, we identify two circuit structures that organize LLM behavior. Opposition circuits appear when RLHF suppresses a pre-training tendency. In safety refusal, about 50 neurons, or 0.014 percent of all neurons, control the refusal template; ablating them changes 80 percent of response formats on 520 AdvBench prompts while producing near-zero harmful compliance, 3 of 520 cases, all with disclaimers. Routing circuits appear for pre-training behaviors distributed through attention. For language selection, residual-stream direction injection switches English to Chinese output on 99.1 percent of 580 benchmark prompts in the 3 of 19 tested models that satisfy three observed conditions: bilingual training, FFN-to-skip signal ratio between 0.3 and 1.1, and linear representability. The same intervention fails on the other 16 models and on math, code, and factual circuits, defining the limits of directional steering. The FFN-to-skip signal ratio, computed from the same two forward passes, distinguishes the two structures and predicts the appropriate intervention. Circuit topology varies by architecture, from Qwen's concentrated FFN bottleneck to Gemma's normalization-shielded circuit. In Qwen3.5-2B, ablating 20 neurons eliminates multi-turn sycophantic capitulation, while amplifying 10 related neurons improves factual correction from 52 percent to 88 percent on 200 TruthfulQA prompts. These results show that perturbation probing offers mechanistic insight into RLHF-organized behavior and a practical toolkit for precision template-layer editing.

In recent years, Multimodal Large Language Models (MLLMs) have achieved remarkable progress on a wide range of multimodal benchmarks. Despite these advances, most existing benchmarks mainly focus on single-image or multi-image comprehension. In real-world scenarios such as document reading, information is often presented as interleaved multimodel contexts. This requires MLLMs not only to recognize the content of individual images, but also to identify relevant textual and visual evidence, establish fine-grained alignments between them, and reason over these aligned signals in interleaved contexts based on contextual evidence. However, there is still a lack of systematic benchmarks for quantifying the fine-grained understanding ability of MLLMs in interleaved image-text contexts. To fill this gap, we propose COHERENCE, a benchmark designed to evaluate the ability of MLLMs to recover fine-grained image-text correspondences in interleaved multimodal contexts. COHERENCE covers interleaved image-text content from four representative domains and contains 6,161 high-quality questions. Moreover, we perform a six-type error analysis, enabling fine-grained attribution of failures in interleaved image-text understanding to the specific capabilities missing in current MLLMs.

Reasoning photo retouching has gained significant traction, requiring models to analyze image defects, give reasoning processes, and execute precise retouching enhancements. However, existing approaches often rely on non-differentiable external software, creating optimization barriers and suffering from high parameter redundancy and limited generalization. To address these challenges, we propose VeraRetouch, a lightweight and fully differentiable framework for multi-task photo retouching. We employ a 0.5B Vision-Language Model (VLM) as the central intelligence to formulate retouching plans based on instructions and scene semantics. Furthermore, we develop a fully differentiable Retouch Renderer that replaces external tools, enabling direct end-to-end pixel-level training through decoupled control latents for lighting, global color, and specific color adjustments. To overcome data scarcity, we introduce AetherRetouch-1M+, the first million-scale dataset for professional retouching, constructed via a new inverse degradation workflow. Furthermore, we propose DAPO-AE, a reinforcement learning post-training strategy that enhances autonomous aesthetic cognition. Extensive experiments demonstrate that VeraRetouch achieves state-of-the-art performance across multiple benchmarks while maintaining a significantly smaller footprint, enabling mobile deployment. Our code and models are publicly available at https://github.com/OpenVeraTeam/VeraRetouch.

As LLMs become credible readers of earnings calls, investor-relations Q\&A, guidance, and disclosure language, supervised financial NLP benchmarks increasingly function as decision evidence for model selection and deployment. A hidden assumption is that gold labels make such evidence objective. This assumption breaks down when the benchmark ruler itself is sensitive to rubric wording, metric choice, or aggregation policy. We study this measurement risk on Japanese Financial Implicit-Commitment Recognition (JF-ICR; a pinned 253-item test split x 4 frontier LLMs x 5 rubrics x 3 temperatures x 5 ordinal metrics). Three findings follow. First, rubric wording materially changes model-assigned labels: R2--R3 agreement ranges from 70.0% to 83.4%, with the dominant movement near the +1 / 0 implicit-commitment boundary. This pattern is consistent with a pragmatic-boundary interpretation, but is not a validated linguistic-causality claim because the present rubric variants confound semantics, examples, and verbosity. Second, not every metric remains informative under the JF-ICR class distribution. Within-one accuracy is too easy because near misses receive credit and the majority class dominates; worst-class accuracy is too noisy because the rarest class has only two examples. Exact accuracy, macro-F1, and weighted \k{appa} are therefore the identifiable metrics under our operational rule. Third, ranking claims become more defensible only after this metric-identifiability audit: Bradley--Terry, Borda, and Ranked Pairs agree on the identifiable metric subset, while the full five-metric sweep produces disagreement on the closest pair. The contribution is not a new leaderboard, but a reporting discipline for supervised financial benchmarks whose gold labels exist and whose evaluation ruler still requires governance.

Simulating optical tactile sensors presents significant challenges due to their high deformability and intricate optical properties. To address these issues and enable a physically accurate simulation, we propose DOT-Sim: Differentiable Optical Tactile Simulation. Unlike prior simulators that rely on simplified models of deformable sensors, DOT-Sim accurately captures the physical behavior of soft sensors by modeling them as elastic materials using the Material Point Method (MPM). DOT-Sim enables rapid calibration of optical tactile sensor simulation using a small number of demonstrations within minutes, which is substantially faster than existing methods. Compared to current baselines, our approach supports much larger and non-linear deformations. To handle the optical aspect, we propose a novel approach to simulating optical responses by learning a residual image relative to the real-world idle state. We validate the physical and visual realism of our method through a series of zero-shot sim-to-real tasks. Our experiments show that DOT-Sim (1) accurately replicates the physical dynamics of a DenseTact optical tactile sensor in reality, (2) generates realistic optical outputs in contact-rich scenarios, (3) enables direct deployment of simulation-trained classifiers in the real world, achieving 85% classification accuracy on challenging objects and 90% accuracy in embedded tumor-type detection, and (4) allows precise trajectory following with a policy trained from demonstrations in simulation, with an average error of less than 0.9 mm.

Recent advances in vision language action (VLA) models have shown remarkable potential for autonomous driving by directly mapping multimodal inputs to control signals. However, previous VLA-based methods have not explicitly exploited the critic capability of VLAs to refine driving decisions, even though such capability has been well demonstrated in other LLM-based domains, thereby limiting their performance in complex closed-loop scenarios. In this work, we present a theoretically inspired two-stage framework, CriticVLA, which extends the role of VLAs from acting to judging. CriticVLA first generates a rough trajectory and then refines it through multimodal evaluation and single-step optimization guided by a VLA-based critic, yielding higher-quality driving behaviors. To support this process, we construct a large-scale synthetic dataset of 12.9 million annotated trajectories covering diverse driving scenarios, which enhances the critic's reasoning and refinement abilities. Extensive closed-loop experiments on the Bench2Drive benchmark show that CriticVLA significantly surpasses state-of-the-art baselines, achieving a 73.33% total success rate and delivering about 30% improvement in challenging scenarios.

Gait recognition has emerged as a compelling biometric modality for surveillance and security applications, offering inherent advantages such as non-intrusiveness, resistance to disguise, and long-range identification capability. However, prevailing approaches struggle to comprehensively capture and exploit the rich biometric cues embedded in human locomotion, particularly under covariate interference including viewpoint variation, clothing change, and carrying conditions. In this paper, we present a high-precision gait recognition framework that deeply extracts and synergistically fuses gait dynamics with body shape characteristics through a multi-branch architecture grounded in deep residual learning. Specifically, we first employ the High-Resolution Network (HRNet) to perform robust skeletal keypoint estimation, preserving fine-grained spatial information even under low-resolution inputs. We then construct three complementary feature branches -- body proportion, gait velocity, and skeletal motion -- from the extracted pose sequences. A 50-layer Residual Network (ResNet-50) backbone is leveraged within a deep feature extraction module to capture hierarchically rich and discriminative representations. To effectively integrate heterogeneous feature streams, we design a Multi-Branch Feature Fusion (MFF) module inspired by channel-wise attention mechanisms, which dynamically allocates contribution weights across branches through learned activation parameters. Extensive experiments on the cross-view multi-condition CASIA-B benchmark demonstrate that our method achieves a Rank-1 accuracy of 94.52\% under normal walking, with the best recognition performance among skeleton-based methods for the coat-wearing condition.

Agentic large language model systems have demonstrated strong capabilities. However, their reliance on language as the universal interface fundamentally limits their applicability to many real-world problems, especially in scientific domains where domain-specific foundation models have been developed to address specialized tasks beyond natural language. In this work, we introduce Eywa, a heterogeneous agentic framework designed to extend language-centric systems to a broader class of scientific foundation models. The key idea of Eywa is to augment domain-specific foundation models with a language-model-based reasoning interface, enabling language models to guide inference over non-linguistic data modalities. This design allows predictive foundation models, which are typically optimized for specialized data and tasks, to participate in higher-level reasoning and decision-making processes within agentic systems. Eywa can serve as a drop-in replacement for a single-agent pipeline (EywaAgent) or be integrated into existing multi-agent systems by replacing traditional agents with specialized agents (EywaMAS). We further investigate a planning-based orchestration framework in which a planner dynamically coordinates traditional agents and Eywa agents to solve complex tasks across heterogeneous data modalities (EywaOrchestra). We evaluate Eywa across a diverse set of scientific domains spanning physical, life, and social sciences. Experimental results demonstrate that Eywa improves performance on tasks involving structured and domain-specific data, while reducing reliance on language-based reasoning through effective collaboration with specialized foundation models.

Human annotators frequently disagree on emotion labels, yet most evaluations of Large Language Model (LLM) emotion annotation collapse these judgments into a single gold standard, discarding the distributional information that disagreement encodes. We ask whether LLMs capture the structure of this disagreement, not just majority labels, by comparing emotion judgment distributions between human annotators and four zero-shot LLMs, plus a fine-tuned RoBERTa baseline, across two complementary benchmarks: GoEmotions and EmoBank, totaling 640,000 LLM responses. Zero-shot models diverge substantially from human distributions, and in-domain fine-tuning, not model scale, is required to close the gap. We formalize a lexical-grounding gradient through a quantitative transparency score that predicts per-category human--LLM agreement: LLMs reliably capture emotions with explicit lexical markers but systematically fail on pragmatically complex emotions requiring contextual inference, a pattern that replicates across both categorical and continuous emotion frameworks. We further propose three lightweight post-hoc calibration methods that reduce the distributional gap by up to 14\%, and provide actionable guidelines for when LLM emotion annotations can, and cannot, substitute for human labeling.

Skin lesion classification is essential for early dermatological diagnosis, yet many existing computer-aided systems rely primarily on dermoscopic images and underutilize the multimodal evidence routinely available in clinical practice. To address this gap, we propose \textbf{JI-ADF}, a trimodal deep learning framework that integrates dermoscopic images, clinical photographs, and structured patient metadata for clinically grounded skin lesion classification. The proposed architecture combines joint multimodal representation learning with modality-specific auxiliary supervision and an adaptive decision fusion mechanism that dynamically calibrates modality contributions on a per-sample basis. To enhance cross-modal reasoning while preserving modality-specific evidence, we further introduce a multimodal fusion attention (MMFA) module. We evaluate JI-ADF on the large-scale MILK10k benchmark, which reflects real-world clinical acquisition conditions and severe class imbalance. The proposed method demonstrates strong and well-balanced performance across lesion categories, improving sensitivity and Dice score while maintaining high specificity and good calibration. Extensive analyses, including modality ablation, calibration evaluation, and Grad-CAM visualization, further confirm the robustness and clinically meaningful behavior of the model. These results indicate that JI-ADF provides a reliable and practical foundation for multimodal skin lesion classification in real-world clinical settings.

Web filtering systems rely on accurate web content classification to block cyber threats, prevent data exfiltration, and ensure compliance. However, classification is increasingly difficult due to the dynamic and rapidly evolving nature of the modern web. Embedding-based zero-shot approaches map content and category descriptions into a shared semantic space, enabling label assignment without labeled training data, but remain highly sensitive to definition quality. Poorly specified or ambiguous definitions create semantic overlap in the embedding space, leading to systematic misclassification. In this paper, we propose a training-free, adaptive iterative definition refinement framework that improves zero-shot web content classification by progressively optimizing category definitions rather than updating model parameters. Using LLMs as feedback-driven definition optimizers, we investigate three refinement strategies namely example-guided, confusion-aware, and history-aware, each refining class descriptions using structured signals from misclassified instances. Furthermore, we introduce a human-labeled benchmark of 10 URL categories with 1,000 samples per class and evaluate across 13 state-of-the-art embedding foundation models. Results demonstrate that iterative definition refinement consistently improves classification performance across diverse architectures, establishing definition quality as a critical and underexplored factor in embedding-based systems. The dataset is available at https://github.com/naeemrehmat/B2MWT-10C.

Hyperspectral image super-resolution is essential for enhancing the spatial fidelity of HSI data, yet existing deep learning methods often struggle with substantial spectral redundancy and the limited non-linear modeling capacity of standard feed-forward networks (FFNs). To address these challenges, we propose Spectral Dynamic Attention Network (SDANet), a framework designed to adaptively suppress redundant spectral interactions. SDANet integrates two key components: 1) Dynamic Channel Sparse Attention (DCSA) module that computes channel-wise correlations and selectively preserves the most informative attention responses through dynamic and data-dependent sparsification. 2) Frequency-Enhanced Feed-Forward Network (FE-FFN) that jointly models spatial and frequency-domain representations to enhance non-linear expressiveness. Extensive experiments on two benchmark datasets demonstrate that SDANet achieves state-of-the-art HISR performance while maintaining competitive efficiency. The code will be made publicly available at https://github.com/oucailab/SDANet.

Hyperspectral image (HSI) and SAR/LiDAR data offer complementary spectral and structural information for land-cover classification. However, their effective fusion remains challenging due to two major limitations: The spectral redundancy in high-dimensional HSI and the heterogeneous characteristics between multi-source data. To this end, we propose Representative Spectral Correlation Network (RSCNet), a novel multi-source image classification framework specifically designed to address the above challenges through spectral selection and adaptive interaction. The network incorporates two key components: (1) Key Band Selection Module (KBSM) that adaptively selects task-relevant spectral bands from the original HSI under cross-source guidance, thereby alleviating redundancy and mitigating information loss from conventional PCA-based spectral reduction. Moreover, the learned band subset exhibits highly discriminative spectral structures that align with discriminative semantic cues, promoting compact yet expressive representations. (2) Cross-source Adaptive Fusion Module (CAFM) that performs cross-source attention weighting and local-global contextual refinement to enhance cross-source feature interaction. Experiments on three public benchmark datasets demonstrate that our RSCNet achieves superior performance compared with state-of-the-art methods, while maintaining substantially lower computational complexity. Our codes are publicly available at https://github.com/oucailab/RSCNet.

Operational weather prediction has long relied on physics-based numerical weather prediction (NWP), whose accuracy comes at the cost of substantial compute and complex simulation workflows. Recent transformer-based forecasters offer efficient data-driven alternatives, however transformers are physics-agnostic models. Additionally, standard transformer encoders evolve representations through discrete layer updates that may be less suited to modeling smooth latent dynamics. In this work, we propose a continuous-depth transformer encoder for weather forecasting that integrates Neural Ordinary Differential Equation (Neural ODE) dynamics within each encoder block. Specifically, we replace discrete residual updates with ODE-based updates solved using adaptive numerical integration. We also introduce a two-branch attention module that combines conventional patch-wise self-attention with an auxiliary branch that applies a derivative operator to attention logits, providing an additional change-sensitive interaction signal. To further align forecasts with governing principles, we propose a customized physics-informed training objective that enforces physical consistency as a soft constraint. We evaluate the proposed method against a standard discrete transformer baseline and an existing continuous-time Neural ODE forecasting variant, demonstrating the importance of PINN-Cast in short term weather forecasting.

We demonstrate stable operation of a thin-film lithium tantalate (TFLT) modulator at very high operating temperatures. We show that the electro-optic modulation and bandwidth of the TFLT modulators are not affected by high-temperature operation, and both waveguide and resonant modulators are DC-bias stable even at 120°C. At higher temperatures, we even observe 10% reduction of the Vπ of the modulator. Our results position TFLT modulators as a strong candidate for uncooled operation in co-packaged optics.

Large language model (LLM)-based coding agents increasingly rely on external memory to reuse prior debugging experience, repair traces, and repository-local operational knowledge. However, retrieved memory is useful only when the current failure is genuinely compatible with a previous one; superficial similarity in stack traces, terminal errors, paths, or configuration symptoms can lead to unsafe memory injection. This paper reframes issue-memory use as a selective, risk-sensitive control problem rather than a pure top-k retrieval problem. We introduce RSCB-MC, a risk-sensitive contextual bandit memory controller that decides whether an agent should use no memory, inject the top resolution, summarize multiple candidates, perform high-precision or high-recall retrieval, abstain, or ask for feedback. The system stores reusable issue knowledge through a pattern-variant-episode schema and converts retrieval evidence into a fixed 16-feature contextual state capturing relevance, uncertainty, structural compatibility, feedback history, false-positive risk, latency, and token cost. Its reward design penalizes false-positive memory injection more strongly than missed reuse, making non-injection and abstention first-class safety actions. In deterministic smoke-scale artifacts, RSCB-MC obtains the strongest non-oracle offline replay success rate, 62.5%, while maintaining a 0.0% false-positive rate. In a bounded 200-case hot-path validation, it reaches 60.5% proxy success with 0.0% false positives and a 331.466 microseconds p95 decision latency. The results show that, for coding-agent memory, the key question is not only which memory is most similar, but whether any retrieved memory is safe enough to influence the debugging trajectory.

Large Language Models (LLMs) are known to acquire reasoning capabilities through shared inference patterns in pre-training data, which are further elicited via Chain-of-Thought (CoT) practices. However, whether fundamental reasoning patterns, such as induction, deduction, and abduction, can be decoupled from specific problem instances remains a critical challenge for model controllability, and for shedding light on reasoning controllability. In this paper, we present the first systematic investigation of this problem through the lens of reasoning conflicts: an explicit tension between parametric and contextual information induced by mandating logical schemata that deviate from those expected for a target task. Our evaluation reveals that LLMs consistently prioritize sensibility over compliance, favoring task-appropriate reasoning patterns despite conflicting instructions. Notably, task accuracy is not strictly determined by sensibility, with models often maintaining high performance even when using conflicting patterns, suggesting a reliance on internalized parametric memory that increases with model size. We further demonstrate that reasoning conflicts are internally detectable, as confidence scores significantly drop during conflicting episodes. Probing experiments confirm that reasoning types are linearly encoded from middle-to-late layers, indicating the potential for activation-level controllability. Leveraging these insights, we steer models towards compliance, increasing instruction following by up to 29%. Overall, our findings establish that while LLM reasoning is anchored to concrete instances, active mechanistic interventions can effectively decouple logical schemata from data, offering a path toward improved controllability, faithfulness, and generalizability.

Tool-calling agents are evaluated on tool selection, parameter accuracy, and scope recognition, yet LLM trajectory assessments remain inherently post-hoc. Disconnected from the active execution loop, such assessments identify errors that are usually addressed through prompt-tuning or retraining, and fundamentally cannot course-correct the agent in real time. To close this gap, we move evaluation into the execution loop at inference time: a specialized reviewer agent evaluates provisional tool calls prior to execution, shifting the paradigm from post-hoc recovery to proactive evaluation and error mitigation. In practice, this architecture establishes a clear separation of concerns between the primary execution agent and a secondary review agent. As with any multi-agent system, the reviewer can introduce new errors while correcting others, yet no prior work to our knowledge has systematically measured this tradeoff. To quantify this tradeoff, we introduce Helpfulness-Harmfulness metrics: helpfulness measures the percentage of base agent errors that feedback corrects; harmfulness measures the percentage of correct responses that feedback degrades. These metrics directly inform reviewer design by revealing whether a given model or prompt provides net positive value. We evaluate our approach on BFCL (single-turn) and Tau2-Bench (multi-turn stateful scenarios), achieving +5.5% on irrelevance detection and +7.1% on multi-turn tasks. Our metrics reveal that reviewer model choice is critical: the reasoning model o3-mini achieves a 3:1 benefit-to-risk ratio versus 2.1:1 for GPT-4o. Automated prompt optimization via GEPA provides an additional +1.5-2.8%. Together, these results demonstrate a core advantage of separating execution and review: the reviewer can be systematically improved through model selection and prompt optimization, without retraining the base agent.

Models of sign language have historically lagged behind those for spoken language (text and speech). Recent work has greatly improved their performance on tasks like sign language translation and isolated sign recognition. However, it remains unclear to what extent existing models capture various linguistic phenomena of sign language, and how well they use cues from the multiple articulators used in sign language (hands, upper body, face). We introduce a new benchmark dataset for American Sign Language, ASL Minimal Translation Pairs (ASL-MTP), divided into multiple types of sign language phenomena and corresponding minimal pairs of translations, for performing such linguistic analyses. As a case study, we use ASL-MTP to analyze a state-of-the-art ASL-to-English translation model. We conduct a targeted analysis of the model by ablating various input cues during training and inference and evaluating on the phenomena in ASL-MTP. Our results show that, while the model performs above chance level on most of the phenomena, it relies strongly on manual cues while often missing crucial non-manual cues.

Democratic discourse analysis systems increasingly rely on multi-agent LLM pipelines in which distinct evaluator models are assigned adversarial roles to generate structured, multi-perspective assessments of political statements. A core assumption is that models will reliably maintain their assigned roles. This paper provides the first systematic empirical test of that assumption using the TRUST pipeline. We develop an epistemic stance classifier that identifies advocate roles from reasoning text without relying on surface vocabulary, and measure role fidelity across 60 political statements (30 English, 30 German) using four metrics: Role Drift Index (RDI), Expected Drift Distance (EDD), Directional Drift Index (DDI), and Entropy-based Role Stability (ERS). We identify two failure modes - the Epistemic Floor Effect (fact-check results create an absolute lower bound below which the legitimizing role cannot be maintained) and Role-Prior Conflict (training-time knowledge overrides role instructions for factually unambiguous statements) - as manifestations of a single mechanism: Epistemic Role Override (ERO). Model choice significantly affects role fidelity: Mistral Large outperforms Claude Sonnet by 28pp (67% vs. 39%) and exhibits a qualitatively different failure mode - role abandonment without polarity reversal - compared to Claude's active switch to the opposing stance. Role fidelity is language-robust. Fact-check provider choice is not universally neutral: Perplexity significantly reduces Claude's role fidelity on German statements (Delta = -15pp, p = 0.007) while leaving Mistral unaffected. These findings have direct implications for multi-agent LLM validation: a system validated without role fidelity measurement may systematically misrepresent the epistemic diversity it was designed to provide.

On-chip silicon photonic coupled cavity arrays (CCA) are a promising platform for quantum simulators, with access to high Quality (Q) factor resonators, tunability, and foundry compatibility. Furthermore, scalable two-dimensional (2D) silicon photonic CCAs allow for simulation of rich physical phenomena via Hamiltonian engineering. However, complete reconstruction of the Hamiltonian is limited by access to cavities in the bulk, with current approaches relying on imaging scattered light from bulk resonators. These approaches often require additional scatterers to be built in, limiting scalability, while also being hampered by imaging technology in the near-infrared range. Instead of these approaches, Hamiltonian tomography algorithms that require homodyne boundary measurements have been demonstrated in literature, however measurements of complex scattering measurements along a CCA boundary have not been shown. Here, we experimentally demonstrate an on-chip homodyne measurement setup along a single boundary of a $3\times 3$ silicon photonic racetrack resonator array and reconstruct the system's edge scattering matrix.

Hybrid-thinking language models expose explicit think and no-think modes, but current designs do not separate them cleanly. Even in no-think mode, models often emit long and self-reflective responses, causing reasoning leakage. Existing work reduces this issue through better data curation and multi-stage training, yet leakage remains because both modes are still encoded in the same feed-forward parameters. We propose Path-Lock Expert (PLE), an architecture-level solution that replaces the single MLP in each decoder layer with two semantically locked experts, one for think and one for no-think, while keeping attention, embeddings, normalization, and the language-model head shared. A deterministic control-token router selects exactly one expert path for the entire sequence, so inference preserves the dense model's per-token computation pattern and each expert receives mode-pure updates during supervised fine-tuning. Across math and science reasoning benchmarks, PLE maintains strong think performance while producing a substantially stronger no-think mode that is more accurate, more concise, and far less prone to reasoning leakage. On Qwen3-4B, for example, PLE reduces no-think reflective tokens on AIME24 from 2.54 to 0.39 and improves no-think accuracy from 20.67% to 40.00%, all while preserving think-mode performance. These results suggest that controllable hybrid thinking is fundamentally an architectural problem, and separating mode-specific feed-forward pathways is a simple and effective solution.

Orbital data centers are being evaluated as solar-powered compute constellations and relay-integrated processing platforms. Their feasibility is not set by orbital solar flux alone, but by simultaneous closure of photovoltaic generation, eclipse recharge, radiative heat rejection, sustained space-to-ground communications, utilization, replacement cadence, and delivered compute-years over finite mission life. This paper derives necessary cluster-level competitiveness conditions using delivered information-technology (IT) electrical power $P_{\rm IT}$, deployed mass per delivered IT power $m_{\rm kW}$ in kg/kW, communication intensity $Γ=D_{\rm sg}/E_{\rm IT}$, sustained communication ceiling $Γ_{\max}$, effective utilization $U_{\rm eff}$, and lifetime penalty $Π_{\rm life}$. For a representative $P_{\rm IT}$=1 MW high-sunlight anchor, the base case gives beginning-of-life photovoltaic area $A^{\rm BOL}_{\rm PV}=5.64 \times 10^3 {\rm m}^2$, radiator area $A_{\rm rad}=2.50 \times 10^3 {\rm m^2}$, and 29.4 kg/kW for photovoltaic, storage, and radiator mass; fixed spacecraft mass raises the total to 34-59 kg/kW. At m_kW ~ 40 kg/kW, a terrestrial infrastructure benchmark of 10-40 k\$/kW allows only 250-1000 \$/kg for the combined launch and spacecraft-build cost before space-to-ground communications, operations, utilization, and lifetime terms are included. That allowance is 3.4-13.5 times below the current public Falcon 9 dedicated low-Earth-orbit launch-price benchmark alone, before spacecraft build is included. Space-native preprocessing and communications-integrated edge compute are credible early regimes; terrestrial-user general compute closes only for low Earth-coupled communication intensity, high effective utilization, long delivered lifetime, and very low combined launch-plus-build cost.

Reinforcement Learning (RL) algorithms exhibit high sample complexity, particularly when applied to Decentralized Partially Observable Markov Decision Processes (Dec-POMDPs). As a response, projects such as SampleFactory, EnvPool, Brax, and IsaacLab migrate parallel execution of classic environments such as MuJoCo and Atari into C++ thread pools or the GPU to decrease the computational cost of environment steps. We are interested in optimizing the decision-level of human-AI joint operations, so we introduce a compute-efficient Dec-POMDP engine natively architected in C++ called Hide-And-Seek-Engine. By employing Data-Oriented Design (DOD) principles, explicit 64-byte cache-line alignment to remove false sharing, and a zero-copy PyTorch memory bridge using pinned memory and Direct Memory Access (DMA), our engine sustains throughput of up to 33,000,000 steps per second (SPS) in a single-agent, 1024-environment, decentralized observations on an AMD Ryzen 9950X (16 cores). Ten agents reduces FPS to 7M SPS with generating random actions contributing 1/3rd the total runtime for reference. The engine achieves a throughput increase of approximately 3,500$\times$ over the baseline single threaded vectorized NumPy implementation and successfully trains cooperative multi-agent policies via PPO, DQN, and SAC in minutes, validating both its performance and generality.

This paper introduces a systematic evaluation framework grounded in the Interagency Language Roundtable (ILR) Skill Level Descriptions and applies it to Claude (Sonnet 4.6) across six languages: English, French, Romanian, Spanish, Italian, and German. We administer a battery of 12 semantically equivalent prompt clusters spanning ILR complexity levels 1 through 3+, collect 216 responses (12 prompts, 6 languages, 3 runs), and analyze outputs through a two-layer methodology combining automated quantitative metrics with expert ILR qualitative assessment. Quantitative analysis reveals that French responses are approximately 30% longer than German responses on identical prompts, and that creative and affective clusters show the highest cross-lingual surface divergence. Qualitative analysis, conducted by a six-language professional with 12 years of ILR/OPI assessment experience, identifies five cross-lingual variation patterns: systematic differences in pragmatic disambiguation strategies, aesthetic and literary tradition divergence in creative output, language-internal technical terminology norms, cultural calibration gaps evidenced by the absence of culture-specific content in favor of culturally neutralized templates, and language-specific institutional referral behavior in emotional support responses. We argue that ILR-informed expert judgment applied to LLM outputs constitutes a novel and underreported evaluation methodology that complements purely computational benchmarks, and that cross-lingual output variation in Claude is interpretable, domain-dependent, and consequential for equitable multilingual AI deployment.

Current LLM safety alignment techniques improve model robustness against adversarial attacks, but overlook whether and how LLMs can recover helpfulness when benign users clarify their intent. We introduce CarryOnBench, the first interactive benchmark that measures whether LLMs can revise their interpretation of user intent and recover utility, while remaining safe through multi-turn conversations. Starting from 398 seemingly harmful queries with benign underlying intents, we simulate 5,970 conversations by varying user follow-up sequences, evaluating 14 models on both intent-aligned utility and safety. CarryOnBench yields 1,866 different conversation flows of 4--12 turns, totaling 23,880 model responses. We design Ben-Util, a checklist-based metric that evaluates how well each model response fulfills the user's benign information need using atomic items. At turn one, models fulfill only 10.5--37.6% of the user's benign information need. When the same query includes the benign intent upfront, models fulfill 25.1--72.1%, confirming that models withhold information due to intent misinterpretation, not limited knowledge. With benign clarifications in multi-turn conversations, 13 of 14 models approach or exceed this single-turn baseline, yet recovery cost varies across models. We identify three failure modes invisible to single-turn evaluations: utility lock-in, where a model rarely updates despite clarification; unsafe recovery, where a model updates at disproportionate safety cost; and repetitive recovery, where a model recycles prior responses rather than providing new information. Moreover, conversations converge to similar harmfulness levels regardless of how conservative the model starts. These findings expose a gap that single-turn evaluations miss -- whether a model is appropriately cautious or simply unresponsive to clarified user intent.

Scientific research has long been human-led, driving new knowledge and transformative technologies through the continual revision of questions, methods and claims as evidence accumulates. Although large language model (LLM)-based agents are beginning to move beyond assisting predefined research workflows, none has yet demonstrated end-to-end autonomous discovery in a real physical system that produces a nontrivial result supported by experimental evidence. Here we introduce Qiushi Discovery Engine, an LLM-based agentic system for end-to-end autonomous scientific discovery on a real optical platform. Qiushi Engine combines nonlinear research phases, Meta-Trace memory and a dual-layer architecture to maintain adaptive and stable research trajectories across long-horizon investigations involving thousands of LLM-mediated reasoning, measurement and revision actions. It autonomously reproduces a published transmission-matrix experiment on a non-original platform and converts an abstract coherence-order theory into experimental observables, providing, to our knowledge, the first observation of this class of coherence-order structure. More importantly, in an open-ended study involving 145.9 million tokens, 3,242 LLM calls, 1,242 tool calls, 163 research notes and 44 scripts, Qiushi Engine proposes and experimentally validates optical bilinear interaction, a physical mechanism structurally analogous to a core operation in Transformer attention. This AI-discovered mechanism suggests a route towards high-speed, energy-efficient optical hardware for pairwise computation. To our knowledge, this is the first demonstration of an AI agentic system autonomously identifying and experimentally validating a nontrivial, previously unreported physical mechanism, marking a milestone for research-level autonomous agents.

As Large Language Model (LLM) agents transition from single-session tools to persistent systems managing longitudinal healthcare journeys, their memory architectures face a critical challenge: reconciling two imperfect sources of truth. The patient's evolving self-report is current but prone to recall bias, while the Electronic Health Record (EHR) is medically validated but frequently stale. General-purpose agent memory systems optimize for coherence by overwriting older facts with the user's latest statement, a pattern that risks safety failures when applied to clinical data. We introduce a Dual-Stream Memory Architecture that strictly separates the patient narrative from the structured clinical record (FHIR), governed by a dedicated Reconciliation Engine that evaluates every extracted memory against the patient's FHIR profile and classifies discrepancies by type, severity, and the specific FHIR resources involved. We evaluate this architecture on 26 patients across 675 longitudinal wellness coaching sessions, using a hybrid dataset that interleaves real provider-patient transcripts with synthetic, FHIR-grounded clinical scenarios. In isolated testing, the engine detects 84.4% of designed clinical discrepancies with 86.7% safety-critical recall. By coupling extraction and reconciliation evaluation on the same data, we directly quantify a 13.6% error cascade, tracing the degradation to clinical details lost during memory extraction from unstructured conversation rather than to downstream classification errors. These findings establish that validating patient-reported memories against clinical records is both feasible and necessary for safe deployment of longitudinal health agents.

Diffusion large language models (dLLMs) offer parallel decoding and bidirectional context, but state-of-the-art dLLMs require billions of parameters for competitive performance. While existing distillation methods for dLLMs reduce inference steps within a single architecture, none address cross-architecture knowledge transfer, in which the teacher and student differ in architecture, attention mechanism, and tokenizer. We present TIDE, the first framework for cross-architecture dLLM distillation, comprising three modular components: (1) TIDAL, which jointly modulates distillation strength across training progress and diffusion timestep to account for the teacher's noise-dependent reliability; (2) CompDemo, which enriches the teacher's context via complementary mask splitting to improve predictions under heavy masking; and (3) Reverse CALM, a cross-tokenizer objective that inverts chunk-level likelihood matching, yielding bounded gradients and dual-end noise filtering. Distilling 8B dense and 16B MoE teachers into a 0.6B student via two heterogeneous pipelines outperforms the baseline by an average of 1.53 points across eight benchmarks, yielding notable gains in code generation, where HumanEval scores reach 48.78 compared to 32.3 for the AR baseline.

Small language models (SLMs) offer computational efficiency for scalable deployment, yet they often fall short of the reasoning power exhibited by their larger counterparts (LLMs). To mitigate this gap, current approaches invoke an LLM to generate tokens at points of reasoning divergence, but these external calls introduce substantial latency and costs. Alternatively, standard distillation is often hindered by the capacity limitation, as SLMs struggle to accurately mimic the LLM's complex generative distribution. We address this dilemma by identifying local sufficiency: at divergence points, the LLM's preferred token consistently resides within the SLM's top-K next-token predictions, even when failing to emerge as the SLM top-1 choice. We therefore propose SELECT TO THINK (S2T), which reframes the LLM's role from open-ended generation to selection among the SLM's proposals, simplifying the supervision signal to discrete candidate rankings. Leveraging this, we introduce S2T-LOCAL, which distills the selection logic into the SLM, empowering it to perform autonomous re-ranking without inference-time LLM dependency. Empirically, we demonstrate that a 1.5B SLM's top-8 candidates capture the 32B LLM's choice with 95% hit rate. Translating this potential into performance, S2T-LOCAL improves greedy decoding by 24.1% on average across benchmarks, effectively matching the efficacy of 8-path self-consistency while operating with single-trajectory efficiency.

Today's AI assistants such as OpenClaw are designed to handle context effectively, making context learning an increasingly important capability for models. As these systems move beyond professional settings into everyday life, the nature of the contexts they must handle also shifts. Real-life contexts are often messy, fragmented, and deeply tied to personal and social experience, such as multi-party conversations, personal archives, and behavioral traces. Yet it remains unclear whether current frontier language models can reliably learn from such contexts and solve tasks grounded in them. To this end, we introduce CL-bench Life, a fully human-curated benchmark comprising 405 context-task pairs and 5,348 verification rubrics, covering common real-life scenarios. Solving tasks in CL-bench Life requires models to reason over complex, messy real-life contexts, calling for strong real-life context learning abilities that go far beyond those evaluated in existing benchmarks. We evaluate ten frontier LMs and find that real-life context learning remains highly challenging: even the best-performing model achieves only 19.3% task solving rate, while the average performance across models is only 13.8%. Models still struggle to reason over contexts such as messy group chat histories and fragmented behavioral records from everyday life. CL-bench Life provides a crucial testbed for advancing real-life context learning, and progress on it can enable more intelligent and reliable AI assistants in everyday life.

LLMs have achieved strong results on both function-level code synthesis and repository-level code modification, yet a capability that falls between these two extremes -- compositional code creation, i.e., building a complete, internally structured class from a specification -- remains underserved. Current evaluations are either confined to isolated functions or rely on manually curated class-level tasks that are expensive to scale and increasingly susceptible to data contamination. We introduce ClassEval-Pro, a benchmark of 300 class-level tasks spanning 11 domains, constructed through an automated three-stage pipeline that combines complexity enhancement, cross-domain class composition, and integration of real-world GitHub code contributed after January 2025. Every task is validated by an LLM Judge Ensemble and must pass test suites with over 90% line coverage. We evaluate five frontier LLMs under five generation strategies. The best model achieves only 45.6% class-level Pass@1, with a 17.7-point gap between the strongest and weakest models, confirming the benchmark's discriminative power. Strategy choice strongly interacts with model capability: structured approaches such as bottom-up improve weaker models by up to 9.4 percentage points, while compositional generation collapses to as low as 1.3%. Error analysis over 500 manually annotated failures reveals that logic errors (56.2%) and dependency errors (38.0%) dominate, identifying cross-method coordination as the core bottleneck.

Claw-style environments support multi-step workflows over local files, tools, and persistent workspace states. However, scalable development around these environments remains constrained by the absence of a systematic framework, especially one for synthesizing verifiable training data and integrating it with agent training and diagnostic evaluation. To address this challenge, we present ClawGym, a scalable framework that supports the full lifecycle of Claw-style personal agent development. Concretely, we construct ClawGym-SynData, a diverse dataset of 13.5K filtered tasks synthesized from persona-driven intents and skill-grounded operations, paired with realistic mock workspaces and hybrid verification mechanisms. We then train a family of capable Claw-style models, termed ClawGym-Agents, through supervised fine-tuning on black-box rollout trajectories, and further explore reinforcement learning via a lightweight pipeline that parallelizes rollouts across per-task sandboxes.To support reliable evaluation, we further construct ClawGym-Bench, a benchmark of 200 instances calibrated through automated filtering and human-LLM review. Relevant resources will be soon released at https://github.com/ClawGym.

Origami-inspired robotic grippers have shown promising potential for object manipulation tasks due to their compact volume and mechanical flexibility. However, robust capture of objects with random shapes in dynamic working environments often comes at the cost of additional actuation channels and control complexity. Here, we introduce a tendon-driven origami tentacle gripper capable of universal object gripping by exploiting a synergy between local, deterministic deformation programming and global, stochastic entanglements. Each origami tentacle is made by cutting thin Mylar sheets; It features carefully placed holes for routing an actuation tendon, origami creases for controlling the deformation, and a tapered shape. By tailoring these design features, one can prescribe the shrinking, bending, and twisting deformation, eventually creating deterministic coiling with a simple tendon pull. Then, when multiple coiling tentacles are placed in proximity, stochastic entanglement emerges, allowing the tentacles to braid, knot, and grip objects with random shapes. We derived a simulation model by integrating origami mechanics with Cosserat rods to correlate origami design, tendon deformation, and their collective gripping performance. Then, we experimentally tested how these coiling and entangling origami tentacles can grasp objects under gravity and in water. A stow-and-release deployment mechanism was also tested to simulate in-orbit grasping. Overall, the entertaining origami tentacle gripper presents a new strategy for robust object grasping with simple design and actuation.

The Hypencoder, proposed by Killingback et al., is a retrieval framework that replaces the fixed inner-product scoring function used in standard bi-encoders with a query-specific neural network (the $q$-net), whose weights are generated by a hypernetwork from the contextualized query embeddings. This design enables more expressive relevance estimation while preserving independent query and document encoding. In this work, we conduct a reproducibility study of the Hypencoder and extend the original analysis in three directions. Our reproduction confirms that the Hypencoder outperforms a similarly trained bi-encoder baseline on in-domain and out-of-domain benchmarks, and that the proposed efficient search algorithm substantially reduces query latency with minimal performance loss. On hard retrieval tasks, we find partial support: the Hypencoder outperforms the baseline on DL-Hard and FollowIR, but not on TREC TOT, where checkpoint incompatibility and fine-tuning sensitivity complicate full verification. Beyond reproduction, we investigate three extensions: (i)~integrating alternative pre-trained encoders into the Hypencoder framework, where we find that performance gains depend on the encoder and fine-tuning strategy; (ii)~comparing query latency against a Faiss-based bi-encoder pipeline, revealing that standard bi-encoder retrieval remains faster under both exhaustive and efficient search settings; and (iii)~evaluating adversarial robustness, where we find that the $q$-net's non-linear scoring does not provide a consistent robustness disadvantage over inner-product scoring. Our code is publicly available at https://github.com/arneeichholtz/Hypencoder-reprod.

Large language models (LLMs) acquire most of their factual knowledge during the pre-training stage, through next token prediction. Subsequent stages of post-training often introduce new facts outwith the parametric knowledge, giving rise to hallucinations. While it has been demonstrated that supervised fine-tuning (SFT) on new knowledge may exacerbate the problem, the underlying mechanisms are still poorly understood. We conduct a controlled fine-tuning experiment, focusing on closed-book QA, and find latent directions that causally contribute to hallucinations. Specifically, we fine-tune Llama 3.1 8B, Gemma 2 9B and Mistral 7B v03 on seven distinct single QA datasets, controlling for the percentage of new knowledge and number of training epochs. By measuring performance on the test set, we validate that incrementally introducing new knowledge increases hallucinations, with the effect being more pronounced with prolonged training. We leverage pre-trained sparse autoencoders (SAEs) to analyze residual stream activations across various checkpoints for each model and propose Monotonic Relationship Feature Identification (MoRFI) for capturing causally relevant latents. MoRFI filters SAE features that respond monotonically to controlled fine-tuning data mixtures of a target property. Our findings show that exposure to unknown facts disrupts the model's ability to retrieve stored knowledge along a set of directions in the residual stream. Our pipeline reliably discovers them across distinct models, recovering knowledge through single-latent interventions.

Many of the thousands of attested languages share common configurations of features, creating a spectrum from typologically very rare (e.g., object-verb-subject word order) or impossible languages to very common combinations of features (e.g., subject-object-verb word order). One central question is under what conditions such typological tendencies can be predicted, and specifically whether the learning bias of language models (LMs) is sufficient to reproduce such patterns. In this study, we add one dimensionality to such analysis -- the learning scenario for LMs -- to explore its interaction with the inductive bias of LMs. Specifically, as a first study, we examine the effect of curriculum learning (CL), as a developmentally motivated learning scenario, i.e., starting with simpler sentences rather than randomly-ordered input. We expand existing LM-based exploration (El-Naggar et al., 2025a,b) with a simple CL variant and find that CL substantially impacts the apparent inductive bias of LMs.

Predictive safety filters (PSFs) leverage model predictive control to enforce constraint satisfaction during deep reinforcement learning (RL) exploration, yet their reliance on first-principles models or Gaussian processes limits scalability and broader applicability. Meanwhile, model-based RL (MBRL) methods routinely employ probabilistic ensemble (PE) neural networks to capture complex, high-dimensional dynamics from data with minimal prior knowledge. However, existing attempts to integrate PEs into PSFs lack rigorous uncertainty quantification. We introduce the Uncertainty-Aware Predictive Safety Filter (UPSi), a PSF that provides rigorous safety predictions using PE dynamics models by formulating future outcomes as reachable sets. UPSi introduces an explicit certainty constraint that prevents model exploitation and integrates seamlessly into common MBRL frameworks. We evaluate UPSi within Dyna-style MBRL on standard safe RL benchmarks and report substantial improvements in exploration safety over prior neural network PSFs while maintaining performance on par with standard MBRL. UPSi bridges the gap between the scalability and generality of modern MBRL and the safety guarantees of predictive safety filters.

Operating and maintaining (O&M) large-scale online engine systems (search, recommendation, advertising) demands substantial human effort for release monitoring, alert response, and root cause analysis. While LLM-based agents are a natural fit for these tasks, the deployment bottleneck is not reasoning capability but orchestration: selecting, for each operational event, the relevant data (metrics, logs, change events) and the applicable operational knowledge (handbook rules and practitioner experience). Feeding all signals indiscriminately causes dilution and hallucination, while manually curating the event-to-(data, knowledge) mapping is intractable under dozens of daily releases. We present Bian Que, an agentic framework with three contributions: (i) a \emph{unified operational paradigm} abstracting day-to-day O&M into three canonical patterns: release interception, proactive inspection, and alert root cause analysis; (ii) \emph{Flexible Skill Arrangement}, where each Skill specifies which data and knowledge to retrieve for a given business-module context and can be automatically generated and updated by LLMs or iteratively refined through natural-language instructions from on-call engineers; (iii) a \emph{unified self-evolving mechanism} in which one correction signal drives two parallel pathways, case-memory-to-knowledge distillation and targeted Skill refinement. Deployed on the e-commerce search engine of KuaiShou, the major short-video platform in China, Bian Que reduces alert volume by 75%, achieves 80% root-cause analysis accuracy, and cuts mean time to resolution by over 50%. Our framework achieves 99.0% pass rate on offline evaluations. Our code is available at https://github.com/benchen4395/BianQue_Assistant.

RL post-training of frontier language models is increasingly bottlenecked by autoregressive rollout generation, making rollout acceleration a central systems challenge. Many existing efficiency methods improve throughput by changing the rollout or optimization regime, for example, through off-policy execution, replay, or lower-precision generation. We study speculative decoding as a lossless acceleration primitive for RL rollouts that preserves the target model's output distribution. We implement speculative decoding in NeMo-RL with a vLLM backend, supporting both synchronous and asynchronous pipelines and enabling speculation during RL rollouts. This benefit is realizable across speculation mechanisms, such as pretrained MTP heads, small external draft models or even techniques such as Eagle3, which are traditionally applied after RL phase. This yields a deployment path for state-of-the-art speculative decoding inside RL training. In a reasoning post-training workload at 8B scale under synchronous RL, speculative decoding improves rollout throughput by 1.8x. Using a high-fidelity performance simulator, we project that combining speculative decoding with asynchronous RL yields up to 2.5x end-to-end training speedup at 235B scale.

Parametric Retrieval-Augmented Generation (PRAG) encodes external documents into lightweight parameter modules that can be retrieved and merged at inference time, offering a promising alternative to in-context retrieval augmentation. Despite its potential, many PRAG implementations train document adapters with task-supervised objectives, which may cause each adapter to encode both document-specific facts and reusable task-solving behavior. This entanglement may make adapter composition less reliable: when multiple adapters are merged at inference time, their overlapping task behaviors can accumulate together with document-specific updates, potentially making the merged adapter less stable and less focused on the intended document knowledge. To examine this issue, we explore Orthogonal Subspace Decomposition (OSD), an adapter-training setup that separates reusable task behavior from document-specific knowledge adapters. Concretely, we first train a Task LoRA to capture reusable task behavior, and then train document LoRAs to encode document-specific knowledge in a orthogonal subspace. This setup provides a controlled way to examine how orthogonalizing task and document LoRA updates affects adapter composition in multi-document PRAG. Experiments across multiple knowledge-intensive tasks and model scales suggest that this orthogonalization strategy can improve compositional robustness in parametric RAG, especially when multiple document adapters are merged.

This paper investigates the influence of interfaces on the performance of finite-sized mechanical metamaterial structures for vibration damping applications. The metamaterial structures are designed in a sandwich configuration in which two homogeneous plates are connected to a metamaterial array. We test four different arrays that are obtained from the same metamaterial by differently cutting the metamaterial's unit cell at the metamaterial/plate interface. When the four unit cells are periodically repeated in space, they create the same infinitely large metamaterial with an identical mechanical response. In finite-sized structures, however, the different interfaces between the metamaterial array and the plates~--~called ``material interfaces''~--~and between the metamaterial and the air~--~called ``free interfaces''~--~strongly affect the specimen's vibration transmission characteristics. Using experimental measurements and validated finite-element (FE) models, we demonstrate a significant influence of the different types of interfaces on the global responses and local displacement fields of the structures. We also demonstrate the presence of a vibroacoustic coupling in the structures which also depends on the type of metamaterial/plate interfaces. Furthermore, we explore optimization strategies for enhancing the vibration damping performance of the metamaterial structures considering not only the metamaterial array but also the adjacent structures (the homogeneous plates). A comparison with benchmark cases illustrates the optimization potential that the interfaces' design offers for the vibration damping capability of finite-sized metamaterial structures. We show that optimizing the type of targeted interfaces can shift a metamaterial's response from underperforming to significantly outperforming compared to classical solutions for noise and vibration damping in civil engineering.

The rise of machine learning and additive manufacturing has enabled the design of architected materials with tailored properties that surpass those of natural materials. Inverse design offers a data-efficient alternative to trial-and-error methods, yet most existing approaches depend on either large datasets or scarce high-fidelity data from simulations and experiments. These requirements pose a particular challenge for architected materials with nonlinear mechanical responses, where capturing complex deformation modes requires expensive evaluations. To address this, a Multi-Fidelity Bayesian Optimisation (MFBO) framework for the inverse design of cellular composites that directly targets their full nonlinear response is introduced. By integrating information from multiple fidelity sources and scalarising the response using a similarity score, the framework enables efficient exploration of the design space while reducing reliance on costly evaluations. As a proof of concept, the method is applied to spinodoid cellular composites using finite element models, validated with compression tests on short carbon-fibre reinforced PET-G composites. Four target responses were considered, with three multi-fidelity strategies benchmarked against a standard single-fidelity approach. Across all cases, MFBO achieved higher similarity scores and consistently recovered the targeted responses, outperforming the single-fidelity baseline under the same evaluation budget, while also successfully recovering all targeted responses. These results demonstrate the effectiveness of MFBO for inverse design of stochastic architected materials, where high-quality data is scarce but lower-cost proxies exist. By efficiently navigating complex design spaces, MFBO enables the creation of cellular composites with precisely tailored nonlinear mechanical behaviour.

Large reasoning models such as DeepSeek-R1 and OpenAI o1 generate extended chains of thought spanning thousands of tokens, yet their integration with retrieval-augmented generation (RAG) remains fundamentally misaligned. Current RAG systems optimize for providing context before reasoning begins, while reasoning models require evidence injection during multi-step inference chains. We introduce ReaLM-Retrieve, a reasoning-aware retrieval framework that addresses this mismatch through three key innovations: (1) a step-level uncertainty detector that identifies knowledge gaps at reasoning-step granularity rather than token or sentence level; (2) a retrieval intervention policy that learns when external evidence maximally benefits ongoing reasoning; and (3) an efficiency-optimized integration mechanism that reduces per-retrieval overhead by 3.2x compared to naive integration. Experiments on MuSiQue, HotpotQA, and 2WikiMultiHopQA demonstrate that ReaLM-Retrieve achieves on average 10.1% absolute improvement in answer F1 over standard RAG (range: 9.0-11.8% across the three benchmarks) while reducing retrieval calls by 47% compared to fixed-interval approaches like IRCoT (all improvements significant at p<0.01, paired bootstrap). On the challenging MuSiQue benchmark requiring 2-4 hop reasoning, our method achieves 71.2% F1 with an average of only 1.8 retrieval calls per question. Analysis shows that ReaLM-Retrieve also improves retrieval quality itself, achieving 81.3% Recall@5 with consistently higher precision and MRR than fixed-interval baselines on supporting evidence, establishing new state-of-the-art efficiency-accuracy trade-offs for reasoning-intensive retrieval tasks.

Autonomous LLM agents increasingly operate in long-horizon, interactive settings where success depends on reusing experience accumulated over extended histories. However, existing agent memory systems are fundamentally constrained by text-context budgets: storing or revisiting raw trajectories is prohibitively token-expensive, while summarization and text-only retrieval trade token savings for information loss and fragmented evidence. To address this limitation, we propose Optical Context Retrieval Memory (OCR-Memory), a memory framework that leverages the visual modality as a high-density representation of agent experience, enabling retention of arbitrarily long histories with minimal prompt overhead at retrieval time. Specifically, OCR-Memory renders historical trajectories into images annotated with unique visual identifiers. OCR-Memory retrieves stored experience via a \emph{locate-and-transcribe} paradigm that selects relevant regions through visual anchors and retrieves the corresponding verbatim text, avoiding free-form generation and reducing hallucination. Experiments on long-horizon agent benchmarks show consistent gains under strict context limits, demonstrating that optical encoding increases effective memory capacity while preserving faithful evidence recovery.

Electric truck operations require routing decisions that remain feasible under limited battery range, long charging times, travel and energy consumption, and competition for shared charging infrastructure. These features make electric truck routing a coupled logistics and energy problem, limiting the practicality of heuristics-based methods and rendering them computationally infeasible at scale. This paper proposes a learning-based framework for the stochastic electric truck routing under charging constraints and operational uncertainty. The problem, solved by Reinforcement Learning, is formulated as an event-driven semi-Markov decision process with shared charging resources, stochastic travel and energy requirements, and realistic nonlinear fast-charging behavior. To support learning in this setting, a graph-based representation of system state and feasible decisions is introduced, together with a rule-based action mask that restricts policies to operationally admissible actions; thus, improving training efficiency. Building on this formulation, an event-driven simulation environment is developed that supports both Reinforcement Learning and benchmarking against heuristic and mathematical programming baselines. Computational experiments across a range of fleet sizes show that the proposed learning-based algorithm consistently outperforms baselines and attains performance close to optimization benchmarks in many settings, while preserving high success rates under charging congestion and uncertainty.

Multi-agent deliberation systems using large language models (LLMs) are increasingly proposed for policy simulation, yet they suffer from artificial consensus: evaluator agents converge on the same option regardless of their assigned value perspectives. We present the AI Council, a three-phase deliberation framework, and conduct 120 deliberations across two policy scenarios to test two interventions. First, architectural heterogeneity (assigning a different 7-9B parameter model to each value perspective) significantly reduces first-choice concentration compared to a homogeneous baseline (child welfare: 70.9% to 46.1%, p < 0.001, r = 0.58; housing: 46.0% to 22.9%, p < 0.001, r = 0.50). This contrasts with accuracy-oriented multi-agent debate, where heterogeneity does not reduce convergence, suggesting model diversity operates differently when no objectively correct answer exists. Second, coherence validation (using a frontier model to assess whether each evaluator's reasoning is grounded in its assigned values) reveals a fidelity-diversity tradeoff: on a scenario with a dominant option, it further reduces concentration (46.1% to 40.8%, p = 0.004), but on a scenario with genuinely competitive options, it increases concentration (22.9% to 26.6%, p = 0.96) by amplifying high-coherence evaluators who cluster on one option. This tradeoff may be a general property of multi-agent systems employing quality weighting. We report negative results from three failed Delphi designs, demonstrate that 8B models exhibit binary rather than graded responses to counter-arguments, and propose the trustworthy tension rate as a diagnostic measure of small-model deliberation capabilities.

Large Language Model (LLM)-based agents exhibit systemic failures in compositional generalization, limiting their robustness in interactive environments. This work introduces AGEL-Comp, a neuro-symbolic AI agent architecture designed to address this challenge by grounding actions of the agent. AGEL-Comp integrates three core innovations: (1) a dynamic Causal Program Graph (CPG) as a world model, representing procedural and causal knowledge as a directed hypergraph; (2) an Inductive Logic Programming (ILP) engine that synthesizes new Horn clauses from experiential feedback, grounding symbolic knowledge through interaction; and (3) a hybrid reasoning core where an LLM proposes a set of candidate sub-goals that are verified for logical consistency by a Neural Theorem Prover (NTP). Together, these components operationalize a deduction--abduction learning cycle: enabling the agent to deduce plans and abductively expand its symbolic world model, while a neural adaptation phase keeps its reasoning engine aligned with new knowledge. We propose an evaluation protocol within the \texttt{Retro Quest} simulation environment to probe for compositional generalization scenarios to evaluate our AGEL agent. Our findings clearly indicate the better performance of our AGEL model over pure LLM-based models. Our framework presents a principled path toward agents that build an explicit, interpretable, and compositionally structured understanding of their world.

In multi-agent systems, should limited resources be concentrated into a few capable agents or distributed among many simpler ones? This work formulates the split over $n$ resource sharing problem where a group of $n$ agents equally shares a common resource (e.g., monetary budget, computational resources, physical size). We present a case study in multi-agent coverage where the area of the disk-shaped footprint of agents scales as $1/n$. A formal analysis reveals that the initial coverage rate grows with $n$. However, if the speed of agents decreases proportionally with their radii, groups of all sizes perform equally well, whereas if it decreases proportionally with their footprints, a single agent performs best. We also present computer simulations in which resource splitting increases the failure rates of individual agents. The models and findings help identify optimal distributiveness levels and inform the design of multi-agent systems under resource constraints.

Consumers are increasingly delegating purchase decisions to AI agents, providing natural-language descriptions of their preferences and identity. We argue that these representations constitute an information channel, role coherence, through which sellers can infer willingness to pay without explicit disclosure by the buyer agent, leading to preference leakage. In an experiment where a language-model buyer agent shops on behalf of a verbal consumer profile, we show that seller-side inference from dialogue alone recovers willingness to pay nearly one-for-one. Comparing this setting to a numeric-budget condition with confidentiality instructions cleanly isolates role coherence as distinct from instruction-following failure. Because this leakage arises from delegation itself, it cannot be mitigated at the prompt level. Instead, we propose architectural interventions that trade off personalization against preference privacy.

Autonomous AI agent ecosystems require stronger mechanisms for secure discovery, identity verification, capability attestation, and policy governance. Current deployments frequently lack (1) uniform agent discovery, (2) cryptographic agent authentication, (3) capability proofs that protect secrets, and (4) enforceable policy controls. This paper presents an implementation-oriented proof of concept for the Agent Name Service (ANS), a DNS-inspired trust layer for AI agent discovery and interoperability in Kubernetes, grounded in the ANS protocol specification~\cite{huang2025ans}. The implementation uses Decentralized Identifiers (DIDs), Verifiable Credentials (VCs), policy-as-code enforcement with Open Policy Agent (OPA), and Kubernetes-native integration patterns (CRDs, admission controls, service mesh integration). In a demo research environment (3-node cluster, 50-agent workflow simulation), we observe sub-10ms response in demonstrated service paths and full success for scripted demo deployment scenarios. We explicitly scope these findings as proof-of-concept evidence rather than production certification. We further provide a threat model, assumptions, and limitations to separate implemented evidence from protocol-defined and roadmap capabilities. The result is an evidence-grounded pathway from ANS protocol concepts to reproducible engineering practice for secure multi-agent systems.

We develop a physics-informed learning framework for energy-shaping control of port-Hamiltonian (pH) systems from trajectory data. The proposed approach {co-learns} a pH system model and an optimal energy-balancing passivity-based controller (EB-PBC) through alternating optimization with policy-aware data collection. At each iteration, the system model is refined using trajectory data collected under the current control policy, and the controller is re-optimized on the updated model. Both components are parameterized by neural networks that embed the pH {dynamics} and EB-PBC structure, ensuring interpretability in terms of energy {interactions}. The learned controller renders the closed-loop system inherently passive and provably stable, and exploits passive plant dynamics without canceling the natural potential. A dissipation regularization enforces strict energy decay during training, thereby enhancing robustness to sim-to-real gaps. The proposed framework is validated on state-regulation and swing-up tasks for planar and torsional pendulum systems.

We study reliability in autonomous language-model agents that translate user mandates into validated tool actions under real capital. The setting is DX Terminal Pro, a 21-day deployment in which 3,505 user-funded agents traded real ETH in a bounded onchain market. Users configured vaults through structured controls and natural-language strategies, but only agents could choose normal buy/sell trades. The system produced 7.5M agent invocations, roughly 300K onchain actions, about $20M in volume, more than 5,000 ETH deployed, roughly 70B inference tokens, and 99.9% settlement success for policy-valid submitted transactions. Long-running agents accumulated thousands of sequential decisions, including 6,000+ prompt-state-action cycles for continuously active agents, yielding a large-scale trace from user mandate to rendered prompt, reasoning, validation, portfolio state, and settlement. Reliability did not come from the base model alone; it emerged from the operating layer around the model: prompt compilation, typed controls, policy validation, execution guards, memory design, and trace-level observability. Pre-launch testing exposed failures that text-only benchmarks rarely measure, including fabricated trading rules, fee paralysis, numeric anchoring, cadence trading, and misread tokenomics. Targeted harness changes reduced fabricated sell rules from 57% to 3%, reduced fee-led observations from 32.5% to below 10%, and increased capital deployment from 42.9% to 78.0% in an affected test population. We show that capital-managing agents should be evaluated across the full path from user mandate to prompt, validated action, and settlement.

Autonomous agents acting in realistic Multi-Agent Systems (MAS) should be able to adapt during their execution. Standard strategic logics, such as Alternating-time Temporal Logic (ATL), model agents' state- or history-dependent behaviour. However, the dynamic treatment of agents' available actions and their knowledge of required actions is still rarely addressed. In this paper, we introduce ATL with Dynamic Actions (ATL-D), which models the process of granting and revoking actions, and its extension ATEL-D, which captures how such updates affect agents' knowledge. Beyond the conceptual contribution, we provide several technical results: we analyse the expressivity of our logic in relation to ATL, study its relation to normative systems, and provide complexity results for relevant computational problems.

As LLM applications grow more complex, developers are increasingly adopting multi-agent architectures to decompose workflows into specialized, collaborative components, introducing structure that constrains agent behavior and exposes useful semantic predictability. Unlike traditional LLM serving, which operates under highly dynamic and uncertain conditions, this structured topology enables opportunities to reduce runtime uncertainty -- yet existing systems fail to exploit it, treating agentic workloads as generic traffic and incurring significant inefficiencies. Our analysis of production traces from an agent-serving platform and an internal coding assistant reveals key bottlenecks, including low prefix cache hit rates, severe resource contention from long-context requests, and substantial queuing delays due to suboptimal scaling. To address these challenges, we propose Pythia, a multi-agent serving system that captures workflow semantics through a simple interface at the serving layer, unlocking new optimization opportunities and substantially improving throughput and job completion time over state-of-the-art baselines.

Contact variability, sensing uncertainty, and external disturbances make grasp execution stochastic. Expected-quality objectives ignore tail outcomes and often select grasps that fail under adverse contact realizations. Risk-sensitive POMDPs address this failure mode, but many use particle-filter beliefs that scale poorly, obstruct gradient-based optimization, and estimate Conditional Value-at-Risk (CVaR) with high-variance approximations. We instead formulate grasp acquisition as variational inference over latent contact parameters and object pose, representing the belief with a differentiable Gaussian mixture. We use Gumbel-Softmax component selection and location-scale reparameterization to express samples as smooth functions of the belief parameters, enabling pathwise gradients through a differentiable CVaR surrogate for direct optimization of tail robustness. In simulation, our variational neural belief improves robust grasp success under contact-parameter uncertainty and exogenous force perturbations while reducing planning time by roughly an order of magnitude relative to particle-filter model-predictive control. On a serial-chain robot arm with a multifingered hand, we validate grasp-and-lift success under object-pose uncertainty against a Gaussian baseline. Both methods succeed on the tested perturbations, but our controller terminates in fewer steps and less wall-clock time while achieving a higher tactile grasp-quality proxy. Our learned belief also calibrates risk more accurately, keeping mean absolute calibration error below 0.14 across tested simulation regimes, compared with 0.58 for a Cross-Entropy Method planner.

We consider the one-dimensional quasilinear heat equation with state-dependent heat capacity and thermal conductivity, and design a boundary-output observer based on the backstepping design for a linear heat equation with constant coefficients. Viewing the quasilinear system as a perturbation of the linear one, we establish exponential stability of the origin for the observation error dynamics in $H^1$, with an explicit region of attraction depending on the system parameters, observer gains, and the mismatch between the nonlinear diffusivity and the constant design diffusivity. Importantly, the observation error converges to zero rather than merely to a neighborhood scaling with this mismatch, even though, in contrast to backstepping-based stabilization of nonlinear PDEs, the mismatch need not decay along trajectories and may remain bounded away from zero, acting as a persistent state-dependent multiplicative perturbation. A technical challenge was to perform a sufficiently-fine Lyapunov analysis that does not yield overly conservative results such as mere boundedness of the observation error. Interestingly, while in the linear case the relationship between one of the backstepping observer gains and the convergence rate is monotonic, we show that in the nonlinear setting this is no longer the case: there may exist an optimal value of that gain, beyond which further increases deteriorate the system's performance. Such behavior cannot be predicted without our analysis: one might expect a priori the decay rate to be freely tunable at the expense of a region of attraction that shrinks to zero as the prescribed rate tends to infinity. However, our Lyapunov analysis (supported by numerical experiments) reveals that this intuition is incorrect.

Single-photon light detection and ranging (LiDAR) extends active three-dimensional sensing at the fundamental level and has found applications in extreme environments involving long-range operation, low-reflectance targets, and adverse visibility. However, the acquired measurements often give rise to single-photon point clouds that are sparse, spatially non-uniform, and corrupted by outliers and depth distortions, making multi-view registration challenging especially when sensor poses are not accurately known. In this work, we present a geometry-intensity coupled registration framework (GIC-Reg) of pose-free multi-view fusion for single-photon sensing. It is established by combining physical-aware preprocessing, joint geometry-intensity grid feature aggregation, global matching, and local ambiguity disambiguation to estimate inter-view rigid transformations and hence to construct a globally consistent reconstruction. On the synthetic benchmark, it admits the lowest relative rotation error (RRE), relative translation error, and root mean square error across all background-noise and dropout rates, in comparison to baselines. Notably, under the most degraded dropout, it reduces the RRE from $13.167^\circ$ to $8.459^\circ$ compared with the learning-based baseline. Furthermore, experimental results on real multi-view data acquired at about 80~m show that it achieves more reliable global orientation and local alignment. Our results show that photon intensity provides an effective physical cue for stabilizing multiview registration in single-photon point cloud, and thus our work aids significant progress in exploring practical utility of single-photon sensing.

During the execution of Multi-Agent Path Finding (MAPF) plans in real-life applications, the MAPF assumption that the fleet's movement is perfectly synchronized does not apply. Since one or more of the agents may become delayed due to internal or external factors, it is often necessary to use a robust execution method to avoid collisions caused by desynchronization. Robust execution methods - such as the Action Dependency Graph (ADG) - synchronize the execution of risky actions, but often at the expense of increased plan execution cost, because it may require some agents to wait for the delayed agents. In such cases, the execution's cost can be reduced while still preserving safety by finding a new plan either by rescheduling (reordering the agents at crossroads) or the more general replanning capable of finding new paths. However, these operations may be costly, and the new plan may not even lead to lower execution cost than the original plan: for example, the two plans may be the exact same. Therefore, we estimate the benefit that can be achieved by single replanning in scenarios with delayed agents given an immediate state of the execution with a fully connected feed-forward neural network. The input to the neural network is a set of newly designed ADG-based features describing the robust execution's state and the impact of potential delays, and the output is an estimated benefit achievable by replanning. We train and test the network on a new labeled dataset containing 12,000 experiments, and we show that our proposed method is capable of reducing the impact of delays by up to 94.6% of the achievable reduction.

In multi-agent reinforcement learning (MARL), the integration of a communication mechanism, allowing agents to better learn to coordinate their actions and converge on their objectives by sharing information. Based on an interaction graph, a subclass of methods employs graph neural networks (GNNs) to learn the communication, enabling agents to improve their internal representations by enriching them with information exchanged. With growing research, we note a lack of explicit structure and framework to distinguish and classify MARL approaches with communication based on GNNs. Thus, this paper surveys recent works in this field. We propose a generalized GNN-based communication process with the goal of making the underlying concepts behind the methods more obvious and accessible.

Truly chiral phonons are lattice eigenmodes that combine broken mirror symmetry with circular atomic motion. They can mediate angular-momentum-selective interactions in quantum materials, yet directly resolving both their chirality and underlying circular motion remains challenging, especially in high-symmetry crystals. Here we show that symmetry-selective terahertz difference-frequency spectroscopy provides a phase- and polarization-resolved route to identifying truly chiral phonons in a tabletop experiment. Using $α$-quartz as a benchmark, we validate this approach by resolving phonon chirality via chiral-sensitive $χ^{(2)}_{ijk}$ tensor elements ($i \neq j \neq k$), while vector-field detection directly reveals a time-dependent polarization rotation arising from circular ionic motion and thus nonzero angular momentum. Applying the same protocol to tetragonal $α$-TeO$_2$, we isolate chiral $E$-mode resonances below 5~THz and directly verify their circular lattice motion, thereby resolving a symmetry-imposed ambiguity in chiral-phonon identification in fourfold-symmetric crystals. Our results establish symmetry-selective nonlinear terahertz spectroscopy as a general route to identify truly chiral phonons in condensed matter systems.

Embodied agents in safety-critical applications such as Vision-Language Navigation (VLN) rely on multiple interdependent capabilities (e.g., perception, memory, planning, decision), making failures difficult to localize and attribute. Existing testing methods are largely system-level and provide limited insight into which capability deficiencies cause task failures. We propose a capability-oriented testing approach that enables failure detection and attribution by combining (1) adaptive test case generation via seed selection and mutation, (2) capability oracles for identifying capability-specific errors, and (3) a feedback mechanism that attributes failures to capabilities and guides further test generation. Experiments show that our method discovers more failure cases and more accurately pinpoints capability-level deficiencies than state-of-the-art baselines, providing more interpretable and actionable guidance for improving embodied agents.

Accurate and real-time sensing of targets in three-dimensional (3D) environments is essential for modern machine vision, underpinning emerging technologies such as autonomous systems, robotic manipulation, augmented reality, and intelligent surveillance. However, state-of-the-art 3D sensing approaches typically rely on complex postprocessing of multi-view images or LiDAR point clouds, resulting in considerable computational load, power consumption, and latency. To address these challenges, we propose a metasurface-encoder integrated optoelectronic neural network architecture that compresses 3D information into two-dimensional images by encoding depth using double-helix point spread function generated by a metasurface. The depth-encoded images are captured with a conventional monocular camera and subsequently processed by a lightweight shadow ResNet neural network. We experimentally validate the proposed architecture on the MNIST and Vehicle-Image datasets, achieving high accuracy simultaneously in target classification and depth estimation, thereby enabling real-time target tracking. The framework is readily extendable to other depth- or angle-encoding metasurfaces for multidimensional compression and detection. Our results demonstrate the effectiveness of the meta-optic-encoder/electronic-decoder paradigm in significantly reducing network complexity and computational burden while maintaining strong performance for smart vision sensory applications.

In this work, we introduce the Deceptive Resource Allocation Game (DRAG), which studies purposeful deception within a Bayesian game framework. In DRAG, a Defender allocates resources across the true asset and several decoys to influence an Attacker's beliefs and actions, with the goal of diverting the Attacker away from the true asset. We seek to characterize purposeful deception, whereby the Defender deceives only when doing so improves its performance. To this end, we solve for the Perfect Bayesian Nash Equilibrium (PBNE) of the corresponding game. We show that, despite the coupled belief-policy interdependence, the problem admits an efficient, non-iterative linear programming formulation. Numerical results demonstrate that the resulting policies naturally balance effective allocation and belief manipulation, giving rise to purposeful and emergent deceptive behaviors.

Forecasting when AI systems will become capable of meaningfully accelerating AI research is a central challenge for AI safety. Existing benchmarks measure broad capability growth, but may not provide ample early warning signals for recursive self-improvement. We propose measuring AI's capability to autonomously implement end-to-end machine learning pipelines from past AI research breakthroughs, given a minimal task description. By providing a concise task description instead of the full prior work as reference, we hope to better elicit emerging AI research taste. We introduce a proof-of-concept benchmark in which frontier coding agents autonomously implement an AlphaZero-style machine learning pipeline for Connect Four on consumer hardware within a three-hour budget, and we evaluate the resulting game AIs in a round-robin tournament anchored to the Pascal Pons Connect Four solver. Across four agents with eight trials each, we find substantial differentiation: Claude Opus 4.7 won as first-mover against Pons in seven of eight trials, statistically significantly better than the other agents tested, none of which exceeded two of eight. The task, which no frontier agent could reliably complete when we began development in January of 2026, is now near-saturation. Our evaluation also surfaced anomalous behavior in GPT-5.4, which consistently used far less of its allocated time budget than other agents. A follow-up 16-trial probe using shorter, less evaluation-coded prompts substantially increased GPT-5.4's time-budget usage, consistent with but not diagnostic of sandbagging; Bradley-Terry ratings across probe conditions showed only directional differences, despite significant differences in time-budget usage. We release our data, code, and prompts to support reproduction and extension.

Robotic fruit harvesting often fails to reliably detect whether a fruit has been successfully picked, limiting efficiency and increasing crop damage. This problem is difficult due to compliant fruit and grippers, variable stem attachment, and occlusions in orchard environments. Prior work has explored vision-based perception and multi-sensor learning approaches for pick state estimation. However, minimal sensor sets and phase-dependent sensing strategies for accurate pick and slip detection remain largely unexplored. In this work, we design and evaluate a multimodal sensing suite integrated into a compliant suction-based apple gripper. Our approach is unique because it identifies which sensors are most informative at different phases of the pick, enabling predictive detection of failures before they occur. The contributions of this paper are a phase-dependent evaluation of multimodal sensors and the identification of minimal sensor sets for reliable pick state classification. Experiments in a real apple orchard show that Random Forest and Multilayer Perceptron classifiers detect successful picks and impending failures with over 90% accuracy, and Random Forest predicts pick/slip events within 0.09 s of human-annotated ground truth.

Decision-making under changing conditions remains a fundamental challenge in many real-world systems. Existing approaches often fail to generalize across shifting regimes and exhibit unstable behavior under uncertainty. This raises the research question: can retrieval-augmented LLM coordination improve the robustness of modular decision pipelines? We propose MultiHedge, a hybrid architecture where an LLM produces structured allocation decisions conditioned on retrieved historical precedents, and execution is grounded in canonical option strategies. In a controlled evaluation using U.S. equities, we compare MultiHedge to rule-based and learning-based baselines. The key result is that memory-augmented retrieval confers greater robustness and stability than increasing model scale alone. Our paper contributes a controlled computational study showing that memory and architectural design play a central role in robustness in modular decision systems.

We propose VISION-SLS, a method for nonlinear output-feedback control from high-resolution RGB images which provides robust constraint satisfaction guarantees under calibrated uncertainty bounds despite partial observability, sensor noise, and nonlinear dynamics. To enable scalability while retaining guarantees, we propose: (i) a learned low-dimensional observation map from pretrained visual features with state-dependent error bounds, and (ii) a causal affine time-varying output-feedback policy optimized via System Level Synthesis (SLS). We develop a scalable, novel solver for the resulting nonconvex program that leverages sequential convex programming coupled with efficient Riccati recursions. On two simulated visuomotor tasks (a 4D car and a 10D quadrotor) with >= 512 x 512 pixels and a 59D humanoid task with partial observability, our method enables safe, information-gathering behavior that reduces uncertainty while guaranteeing constraint satisfaction with empirically-calibrated error bounds. We also validate our method on hardware, safely controlling a ground vehicle from onboard images, outperforming baselines in safety rate and solve times. Together, these results show that learned visual abstractions coupled with an efficient solver make SLS-based safe visuomotor output-feedback practical at scale. The code implementation of our method is available at https://github.com/trustworthyrobotics/VISION-SLS.

While diffusion models generate high-fidelity video clips, transforming them into coherent storytelling engines remains challenging. Current agentic pipelines automate this via chained modules but suffer from semantic drift and cascading failures due to independent, handcrafted prompting. We present Co-Director, a hierarchical multi-agent framework formalizing video storytelling as a global optimization problem. To ensure semantic coherence, we introduce hierarchical parameterization: a multi-armed bandit globally identifies promising creative directions, while a local multimodal self-refinement loop mitigates identity drift and ensures sequence-level consistency. This balances the exploration of novel narrative strategies with the exploitation of effective creative configurations. For evaluation, we introduce GenAD-Bench, a 400-scenario dataset of fictional products for personalized advertising. Experiments demonstrate that Co-Director significantly outperforms state-of-the-art baselines, offering a principled approach that seamlessly generalizes to broader cinematic narratives. Project Page: https://co-director-agent.github.io/

Accurate estimation of thermospheric mass density is a prerequisite for orbit prediction and space situational awareness, where the upper atmosphere responds nonlinearly to solar and geomagnetic forcing across several orders of magnitude. Physics-based general circulation models resolve this response but are computationally expensive, while empirical models run cheaply but lack a time-evolving atmospheric state. This work couples a data-driven reduced-order thermospheric model with a Kalman filter that assimilates in situ density observations. An autoregressive Sparse Identification of Nonlinear Dynamics with control (SINDy$_c$-AR) reduced-order model derived from the Thermosphere-Ionosphere-Electrodynamics General Circulation Model (TIE-GCM) captures the dominant modes of variability and their dependence on solar and geomagnetic drivers at a fraction of the parent model's cost. Density observations from CHAMP, GRACE, GRACE-FO, GOCE, and Swarm are assimilated across a range of orbital configurations and geomagnetic conditions, with a linear DMDc model evaluated as a reference. Assimilation reduces density estimation error relative to open-loop predictions, most visibly during geomagnetic storms and under single-satellite coverage. SINDy$_c$-AR and DMDc perform comparably on assimilated orbits; on withheld orbits, SINDy$_c$-AR is more accurate in the in-training scenarios while DMDc is better in the out-of-training 2024 Swarm-C case. Benchmarks against NRLMSIS~2.1 and HASDM (2000--2019, where available) show that empirical references can outperform the assimilated model far from the assimilated track, so results are framed as improvements over the open-loop forecast.

The Observational Medical Outcomes Partnership Common Data Model (OMOP CDM), maintained by the Observational Health Data Sciences and Informatics (OHDSI) collaboration, enabled the harmonisation of electronic health records data of nearly one billion patients in 83 countries. Yet generating real-world evidence (RWE) from these repositories remains a manual process requiring clinical, epidemiological and technical expertise. LLMs and multi-agent systems have shown promise for clinical tasks, but RWE automation exposes a fundamental challenge: agentic systems introduce emergent behaviours, coordination failures and safety risks that existing approaches fail to govern. No infrastructure exists to ensure agentic RWE generation is flexible, safe and auditable across the lifecycle. We introduce FastOMOP, an open-source multi-agent architecture that addresses this gap by separating three infrastructure layers, governance, observability and orchestration, from pluggable agent-teams. Governance is enforced at the process boundary through deterministic validation independent of agent reasoning, ensuring no compromised or hallucinating agent can bypass safety controls. Agent teams for phenotyping, study design and statistical analysis inherit these guarantees through controlled tool exposure. We validated FastOMOP using a natural-language-to-SQL agent team across three OMOP CDM datasets: synthetic data from Synthea, MIMIC-IV and a real-world NHS dataset from Lancashire Teaching Hospitals (IDRIL). FastOMOP achieved reliability scores of 0.84-0.94 with perfect adversarial and out-of-scope block rates, demonstrating process-boundary governance delivers safety guarantees independent of model choice. These results indicate that the reliability gap in RWE deployment is architectural rather than model capability, and establish FastOMOP as a governed architecture for progressive RWE automation.

Emerging delay-critical edge AI applications, such as VR perception and real-time video analytics, impose stringent latency and reliability requirements on 5G networks. However, existing mobility management mechanisms are largely reactive and fail to adapt to dynamic network conditions, resulting in suboptimal handover decisions and degraded performance. In this paper, we present TARMM, a 5G Open Radio Access Network (O-RAN) system that optimizes user mobility management for delay-critical edge AI offloading. The core of TARMM is a temporal graph model that captures the spatiotemporal dynamics of the RAN across users and cells, enabling near real-time handover decisions. Building on this representation, we design a multi-agent reinforcement learning (MARL) framework with rule-based action masking and proactive resource preparation to ensure safe, stable, and efficient handovers. We implement TARMM on a multi-cell indoor 5G O-RAN testbed and evaluate it using diverse VR workloads. Extensive experiments show that TARMM reduces tail latency by up to 44% and packet loss by up to 56% compared to state-of-the-art approaches.

The rapid integration of Large Language Models (LLMs) into Multi-Agent Systems (MAS) has significantly enhanced their collaborative problem-solving capabilities, but it has also expanded their attack surfaces, exposing them to vulnerabilities such as prompt infection and compromised inter-agent communication. While emerging graph-based anomaly detection methods show promise in protecting these networks, the field currently lacks a standardized, reproducible environment to train these models and evaluate their efficacy. To address this gap, we introduce Gammaf (Graph-based Anomaly Monitoring for LLM Multi-Agent systems Framework), an open-source benchmarking platform. Gammaf is not a novel defense mechanism itself, but rather a comprehensive evaluation architecture designed to generate synthetic multi-agent interaction datasets and benchmark the performance of existing and future defense models. The proposed framework operates through two interdependent pipelines: a Training Data Generation stage, which simulates debates across varied network topologies to capture interactions as robust attributed graphs, and a Defense System Benchmarking stage, which actively evaluates defense models by dynamically isolating flagged adversarial nodes during live inference rounds. Through rigorous evaluation using established defense baselines (XG-Guard and BlindGuard) across multiple knowledge tasks (such as MMLU-Pro and GSM8K), we demonstrate Gammaf's high utility, topological scalability, and execution efficiency. Furthermore, our experimental results reveal that equipping an LLM-MAS with effective attack remediation not only recovers system integrity but also substantially reduces overall operational costs by facilitating early consensus and cutting off the extensive token generation typical of adversarial agents.

Reliable low-latency communication is a key requirement for mission-critical and mobile autonomous systems, including teleoperation, autonomous navigation, and real-time uplink-dominant telemetry applications. While commercial 5G networks often provide adequate downlink performance, uplink performance in rural deployments may be constrained by radio-resource limitations and uplink power-control mechanisms. This paper presents a comprehensive experimental evaluation of multi-connectivity strategies over commercial 5G Non-Standalone networks, based on measurement campaigns conducted in urban, suburban, and rural environments. The study analyzes per-packet uplink and downlink latency, packet loss, and radio-layer KPIs across two mobile network operators. The measurements indicate that latency and reliability cannot be inferred solely from coverage indicators such as RSRP. In coverage-constrained scenarios, performance appears to be strongly influenced by uplink power-limited operation and partially correlated impairments across operators. Several multi-connectivity strategies are evaluated, including link aggregation, switching-based policies, and conditional packet duplication. A Primary-Anchored Adaptive Failover (PAAF) framework is introduced to selectively activate redundancy based on radio, latency and service cost considerations. The results suggest that Partial Duplication (PD) approaches can approach the reliability of multi-connectivity while substantially reducing duplication overhead in the evaluated rural scenario.

The rapid growth of the low-altitude economy drives increasingly autonomous unmanned aerial vehicle (UAV) operations, giving rise to low-altitude embodied intelligence (LAEI), in which sensing, communication, computation, and control (SC$^3$) are tightly integrated to enable closed-loop interaction, ensuring timely, effective, and safe responses in complex or unknown environments. This article systematically explores the LAEI networks, from its fundamental architecture to the diverse scenarios that it can support. We examine key enabling techniques that sustain timely information exchange and effective decision feedback within the $\text{SC}^3$ closed loop. A representative low-altitude UAV mission in an unknown urban area is presented as a case study, where the UAV provides communication services and performs environmental sensing to inform closed-loop control, illustrating how coordinated $\text{SC}^3$ capabilities enable efficient and responsive operation. By identifying major challenges and outlining future research directions, this work serves as a cornerstone for developing next-generation low-altitude intelligent systems.

Auditing the semantic properties of proprietary data creates a fundamental tension: verification requires transparent access, while proprietary rights demand confidentiality. While Zero-Knowledge Proofs (ZKPs) ensure privacy, they are typically limited to precise algebraic constraints and are ill-suited for verifying qualitative, unstructured properties, such as the logic within a codebase. We propose {\em Agentic Witnessing}, a framework that moves verification from attested execution to {\em attested reasoning}. The system is composed of three agents: a Verifier (who wants to check properties of a dataset), a Prover (who owns the dataset) and an Auditor (that inspects the dataset). The Verifier is allowed to ask a limited number of simple binary true/false questions to the auditor. By isolating an LLM-based Auditor within a Trusted Execution Environment (TEE), the system enables the Verifier to query a Prover's private data via simple Boolean queries, without exposing the raw dataset. The Auditor uses the Model Context Protocol (MCP) to dynamically inspect the target dataset, producing a yes/no verdict accompanied by a cryptographic transcript: a signed hash chain binding the reasoning trace to both the original dataset and the TEE's hardware root of trust. We demonstrate this architecture by automating the artifact evaluation process for 21 peer-reviewed computer science papers with released codebases on GitHub (e.g. Does the codebase implement the system described in the paper?). We verified five high-level properties of these codebases described in the corresponding publications, treating the source code as private. Our results show that TEE-enabled agentic auditing provides a mechanism for privacy-preserving oversight, effectively decoupling qualitative verification from the need for data disclosure.

Process Reward Models (PRMs) have achieved remarkable success in augmenting the reasoning capabilities of Large Language Models (LLMs) within static domains such as mathematics. However, their potential in dynamic data analysis tasks remains underexplored. In this work, we first present a empirical study revealing that general-domain PRMs struggle to supervise data analysis agents. Specifically, they fail to detect silent errors, logical flaws that yield incorrect results without triggering interpreter exceptions, and erroneously penalize exploratory actions, mistaking necessary trial-and-error exploration for grounding failures. To bridge this gap, we introduce DataPRM, a novel environment-aware generative process reward model that (1) can serve as an active verifier, autonomously interacting with the environment to probe intermediate execution states and uncover silent errors, and (2) employs a reflection-aware ternary reward strategy that distinguishes between correctable grounding errors and irrecoverable mistakes. We design a scalable pipeline to construct over 8K high-quality training instances for DataPRM via diversity-driven trajectory generation and knowledge-augmented step-level annotation. Experimental results demonstrate that DataPRM improves downstream policy LLMs by 7.21% on ScienceAgentBench and 11.28% on DABStep using Best-of-N inference. Notably, with only 4B parameters, DataPRM outperforms strong baselines, and exhibits robust generalizability across diverse Test-Time Scaling strategies. Furthermore, integrating DataPRM into Reinforcement Learning yields substantial gains over outcome-reward baselines, achieving 78.73% on DABench and 64.84% on TableBench, validating the effectiveness of process reward supervision. Code is available at https://github.com/zjunlp/DataMind.

Large language model tutors are easy to build in a notebook and hard to run in a real course. We describe ITAS (Intelligent Teaching Assistant System), a multi-agent tutoring system that a graduate quantum computing course used for a semester at Old Dominion University. The system has three layers. The teaching layer is a Spoke-and-Wheel of three parallel specialist agents (Video, Code, Guidance) followed by a Synthesizer, plus a separate autograder that evaluates both the correctness and the approach of checkpoint submissions. The operational layer is four Cloud Run microservices with session state in Cloud SQL and interaction events streamed through Pub/Sub to BigQuery. The feedback layer is a narrow-scope conversational agent that answers instructor questions over per-lesson pseudonymized event streams, addressing what we call the Blind Instructor Problem: LLM tutors accumulate more data about students than the instructor can reach through routine channels. The architecture is a direct response to specific failures of an earlier prototype, and we describe which of those fixes carried forward and which were dropped for this iteration. We report on a pilot deployment (five students, one course, one semester) interpreted as system-behavior evidence rather than learning-outcome evidence: the teaching layer handled 334 chat turns without the task-boundary hallucinations that domain consolidation would have risked, the operational layer captured 10,628 events across five modules, and the feedback layer surfaced two findings the instructor acted on mid-semester. We do not claim the pilot generalizes. We do claim that the system as described is one workable answer to the question of what an LLM-based ITS needs to look like end-to-end to run in a real course.

Quantum computing instructors face a compounding problem: the concepts are counterintuitive, the mathematical formalism is dense, and qualified faculty are scarce outside a small number of well-resourced institutions. Our prior work introduced a knowledge-graph-augmented tutoring prototype with two specialized LLM agents: a Teaching Agent for dynamic interaction and a Lesson Planning Agent for lesson generation. Validated on simulated runs rather than in a real course, that prototype left open whether more aggressive agent specialization would be needed to handle the full range of quantum education tasks under real student load. This paper answers the three questions that the prototype could not answer. Can agent specialization solve the reliability problem in a domain as technically demanding as quantum information science? Can the system run in a real course, not a demonstration? Does the instructor gain actionable intelligence from the deployment? We present ITAS (Intelligent Teaching Assistant System), a multi-agent tutoring system built around four contributions: a five-module QIS curriculum grounded in Watrous's information-first framework, a Spoke-and-Wheel teaching architecture with quantum-specialized agents, a cloud infrastructure designed for production use and regulatory compliance, and a conversational analytics layer for instructors and content developers. Piloted in a quantum computing course at Old Dominion University, the system supports all three answers: deployment evidence is consistent with specialization addressing the task-boundary failures observed in the prototype, cloud infrastructure supports classroom-scale concurrency at sub-textbook cost, and the analytics agent surfaces curriculum gaps the instructor could not otherwise see.

Deploying neural-network control barrier functions (CBFs) on embedded hardware requires evaluating the barrier value and its Lie derivatives along the system vector fields at every control cycle. The standard mechanism for exact gradient extraction, reverse-mode automatic differentiation, constructs a dynamic computational graph whose memory footprint grows with network depth and whose backward traversal obstructs the worst-case execution time analysis required for safety-critical certification. This paper presents a dual-algebraic compiler that extracts the exact barrier value and its Lie derivatives through forward network evaluation alone. Encoding the system state as the real part of a dual number and a target vector field as the dual part, we prove that every affine and componentwise-activation layer admits a dual extension that propagates the exact directional derivative alongside the activation, and that the composed dual-extended network evaluates the exact Jacobian--vector-field product with zero truncation error. We derive closed-form expressions for the dual-pass floating-point operation count and peak memory footprint, prove that the proposed algorithm eliminates dynamic graph allocation, and extend the framework to the second-order Lie derivatives required by relative-degree-two CBFs using hyper-dual arithmetic. An open-source ahead-of-time compiler translates trained neural CBFs into self-contained C++ headers that assemble the complete safety constraint on an ESP32-S3 microcontroller from a statically allocated buffer, with zero dynamic memory allocation and a sub-millisecond cycle budget that supports kilohertz-rate safety filters.

Product mapping, the task of deciding whether two e-commerce listings refer to the same product, is a core problem for price monitoring and channel visibility. In real marketplaces, however, sellers frequently inject promotional keywords, platform-specific tags, and bundle descriptions into titles, causing the same product to appear under many different names. Recent LLM-based and multi-agent frameworks improve robustness and interpretability on such hard cases, but they often rely on expensive external APIs, repeated retrieval, and complex inference-time orchestration, making large-scale deployment costly and difficult in privacy-sensitive enterprise settings. To address these issues, we present EPM-RL, a reinforcement-learning-based framework for building an accurate and efficient on-premise e-commerce product mapping model. Our central idea is to distill high-cost agentic reasoning into a trainable in-house model. Starting from a curated set of product pairs with LLM-generated rationales and human verification, we first perform parameter-efficient fine-tuning (PEFT) on a small student model using structured reasoning outputs. We then further optimize the model with Reinforcement Learning (RL) using an agent-based reward that jointly evaluates output-format compliance, label correctness, reasoning--preference scores from specially designed judge models. Preliminary results show that EPM-RL consistently improves over PEFT-only training and offers a stronger quality--cost trade-off than commercial API-based baselines, while enabling private deployment and lower operational cost. These findings suggest that reinforcement learning can turn product mapping from a high-latency agentic pipeline into a scalable, inspectable, and production-ready in-house system.

Indoor navigation remains a critical accessibility challenge for the blind and low-vision (BLV) individuals, as existing solutions rely on costly per-building infrastructure. We present an agentic framework that converts a single floor plan image into a structured, retrievable knowledge base to generate safe, accessible navigation instructions with lightweight infrastructure. The system has two phases: a multi-agent module that parses the floor plan into a spatial knowledge graph through a self-correcting pipeline with iterative retry loops and corrective feedback; and a Path Planner that generates accessible navigation instructions, with a Safety Evaluator agent assessing potential hazards along each route. We evaluate the system on the real-world UMBC Math and Psychology building (floors MP-1 and MP-3) and on the CVC-FP benchmark. On MP-1, we achieve success rates of 92.31%, 76.92%, and 61.54% for short, medium, and long routes, outperforming the strongest single-call baseline (Claude 3.7 Sonnet) at 84.62%, 69.23%, and 53.85%. On MP-3, we reach 76.92%, 61.54%, and 38.46%, compared to the best baseline at 61.54%, 46.15%, and 23.08%. These results show consistent gains over single-call LLM baselines and demonstrate that our workflow is a scalable solution for accessible indoor navigation for BLV individuals.

Autonomous driving systems often infer pedestrian yielding behavior from geometric and kinematic cues alone, limiting their ability to reason about visual scene context and age-dependent behavioral variability. This limitation can produce delayed interventions in safety-critical encounters and unnecessary braking in benign interactions. This work introduces Vision-Language Model-based Vehicle-Pedestrian Interaction (VLM-VPI), a multimodal reasoning framework for pedestrian intent understanding and yielding-aware control in autonomous driving. The system combines three components: a multimodal perception layer that captures visual and kinematic observations, a reasoning layer that uses Qwen3-VL 8B for visual scene understanding and GPT-OSS 20B for few-shot intent reasoning, and a tiered safety controller that applies age-specific braking margins for children, adults, and seniors. In 112 CARLA scenarios, VLM-VPI achieves 92.3% intent classification accuracy, outperforming a rule-based baseline (78.4%), supervised trajectory models (73.5-82.4%), and a zero-shot LLM configuration (88.4%). Validation on 24 real-world PIE scenarios yields 87.5% accuracy, indicating functional sim-to-real transferability. Across 200 simulation cases, VLM-VPI reduces the false-alarm rate from 7.4% to 2.8% and mean intersection traversal time from 13.5 s to 11.8 s. Conflict occurrences decrease from 124 to 33, while mean minimum time-to-collision improves from 1.92 s to 4.47 s. Demographic-adaptive control further reduces conflicts by 60% for children and 54.5% for seniors compared with uniform control. These results show that an explicit vision-language reasoning layer can improve both safety and efficiency by linking pedestrian intent, demographic context, and vehicle control decisions.

Short term electricity price forecast is essential in competitive power markets, yet electricity price series exhibit high volatility, irregularity, and non-stationarity. This phenomenon is pronounced in the South Australian region of the National Electricity Market, where high renewable penetration drives price volatility and frequent negative price intervals, while structural changes such as the transition to five-minute settlement further complicate forecast. To address these challenges, this study develops a unified benchmark framework. Under identical data preprocessing, feature engineering with lag features, rolling statistics, cyclic temporal encodings, and so on, and an 85% to 15% chronological train test split, six algorithms are systematically compared, including AWMLSTM, CatBoost, GBRT, LSTM, LightGBM, and SVR. The results show that for price prediction, tree-based models, especially GBRT with an R squared value of 0.88, generally outperform LSTM and SVR. However, all models achieve a mean absolute percentage error above 90%, and more than 65% of GBRT predictions have relative errors above 10%, which highlights the inherent difficulty of price forecast. For demand prediction, all models perform substantially better than in price prediction. AWMLSTM and GBRT achieve an R2 value of 0.96 with mean absolute percentage error below 32%, and GBRT has 74.37% of samples within 5% error, while LSTM and SVR perform less accurately in both tasks. Future improvements should focus on hybrid models such as tree plus transformers, data augmentation for extreme events, and error correction to better capture price spikes.