OrangeBot.AI Digest — 2026-02-01

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

Neovim AI agent done right

Agent Orchestration Command Center

The official source code repository for the calibre ebook manager

AI agent toolkit: coding agent CLI, unified LLM API, TUI & web UI libraries, Slack bot, vLLM pods

A Claude Code plugin that automatically captures everything Claude does during your coding sessions, compresses it with AI (using Claude's agent-sdk), and injects relevant context back into future sessions.

The absolute trainer to light up AI agents.

Turn any browser into your terminal & command your agents on the go.

Show usage stats for OpenAI Codex and Claude Code, without having to login.

⚡ Better `pre-commit`, re-engineered in Rust

[ICLR 26] Stable Video Infinity: Infinite-Length Video Generation with Error Recycling

Autonomous scientific discovery with large language model (LLM)-based agents has recently made substantial progress, demonstrating the ability to automate end-to-end research workflows. However, existing systems largely rely on runtime-centric execution paradigms, repeatedly reading, summarizing, and reasoning over large volumes of scientific literature online. This on-the-spot computation strategy incurs high computational cost, suffers from context window limitations, and often leads to brittle reasoning and hallucination. We propose Idea2Story, a pre-computation-driven framework for autonomous scientific discovery that shifts literature understanding from online reasoning to offline knowledge construction. Idea2Story continuously collects peer-reviewed papers together with their review feedback, extracts core methodological units, composes reusable research patterns, and organizes them into a structured methodological knowledge graph. At runtime, underspecified user research intents are aligned to established research paradigms, enabling efficient retrieval and reuse of high-quality research patterns instead of open-ended generation and trial-and-error. By grounding research planning and execution in a pre-built knowledge graph, Idea2Story alleviates the context window bottleneck of LLMs and substantially reduces repeated runtime reasoning over literature. We conduct qualitative analyses and preliminary empirical studies demonstrating that Idea2Story can generate coherent, methodologically grounded, and novel research patterns, and can produce several high-quality research demonstrations in an end-to-end setting. These results suggest that offline knowledge construction provides a practical and scalable foundation for reliable autonomous scientific discovery.

Text-to-image (T2I) models have achieved remarkable success in generating high-fidelity images, but they often fail in handling complex spatial relationships, e.g., spatial perception, reasoning, or interaction. These critical aspects are largely overlooked by current benchmarks due to their short or information-sparse prompt design. In this paper, we introduce SpatialGenEval, a new benchmark designed to systematically evaluate the spatial intelligence of T2I models, covering two key aspects: (1) SpatialGenEval involves 1,230 long, information-dense prompts across 25 real-world scenes. Each prompt integrates 10 spatial sub-domains and corresponding 10 multi-choice question-answer pairs, ranging from object position and layout to occlusion and causality. Our extensive evaluation of 21 state-of-the-art models reveals that higher-order spatial reasoning remains a primary bottleneck. (2) To demonstrate that the utility of our information-dense design goes beyond simple evaluation, we also construct the SpatialT2I dataset. It contains 15,400 text-image pairs with rewritten prompts to ensure image consistency while preserving information density. Fine-tuned results on current foundation models (i.e., Stable Diffusion-XL, Uniworld-V1, OmniGen2) yield consistent performance gains (+4.2%, +5.7%, +4.4%) and more realistic effects in spatial relations, highlighting a data-centric paradigm to achieve spatial intelligence in T2I models.

While Mixture-of-Experts (MoE) architectures have become the standard for sparsity scaling in large language models, they increasingly face diminishing returns and system-level bottlenecks. In this work, we explore embedding scaling as a potent, orthogonal dimension for scaling sparsity. Through a comprehensive analysis and experiments, we identify specific regimes where embedding scaling achieves a superior Pareto frontier compared to expert scaling. We systematically characterize the critical architectural factors governing this efficacy -- ranging from parameter budgeting to the interplay with model width and depth. Moreover, by integrating tailored system optimizations and speculative decoding, we effectively convert this sparsity into tangible inference speedups. Guided by these insights, we introduce LongCat-Flash-Lite, a 68.5B parameter model with ~3B activated trained from scratch. Despite allocating over 30B parameters to embeddings, LongCat-Flash-Lite not only surpasses parameter-equivalent MoE baselines but also exhibits exceptional competitiveness against existing models of comparable scale, particularly in agentic and coding domains.

Manipulating dynamic objects remains an open challenge for Vision-Language-Action (VLA) models, which, despite strong generalization in static manipulation, struggle in dynamic scenarios requiring rapid perception, temporal anticipation, and continuous control. We present DynamicVLA, a framework for dynamic object manipulation that integrates temporal reasoning and closed-loop adaptation through three key designs: 1) a compact 0.4B VLA using a convolutional vision encoder for spatially efficient, structurally faithful encoding, enabling fast multimodal inference; 2) Continuous Inference, enabling overlapping reasoning and execution for lower latency and timely adaptation to object motion; and 3) Latent-aware Action Streaming, which bridges the perception-execution gap by enforcing temporally aligned action execution. To fill the missing foundation of dynamic manipulation data, we introduce the Dynamic Object Manipulation (DOM) benchmark, built from scratch with an auto data collection pipeline that efficiently gathers 200K synthetic episodes across 2.8K scenes and 206 objects, and enables fast collection of 2K real-world episodes without teleoperation. Extensive evaluations demonstrate remarkable improvements in response speed, perception, and generalization, positioning DynamicVLA as a unified framework for general dynamic object manipulation across embodiments.

Recent advances in Vision Language Models (VLMs) have driven significant progress in visual reasoning. However, open-source VLMs still lag behind proprietary systems, largely due to the lack of high-quality reasoning data. Existing datasets offer limited coverage of challenging domains such as STEM diagrams and visual puzzles, and lack consistent, long-form Chain-of-Thought (CoT) annotations essential for eliciting strong reasoning capabilities. To bridge this gap, we introduce MMFineReason, a large-scale multimodal reasoning dataset comprising 1.8M samples and 5.1B solution tokens, featuring high-quality reasoning annotations distilled from Qwen3-VL-235B-A22B-Thinking. The dataset is established via a systematic three-stage pipeline: (1) large-scale data collection and standardization, (2) CoT rationale generation, and (3) comprehensive selection based on reasoning quality and difficulty awareness. The resulting dataset spans STEM problems, visual puzzles, games, and complex diagrams, with each sample annotated with visually grounded reasoning traces. We fine-tune Qwen3-VL-Instruct on MMFineReason to develop MMFineReason-2B/4B/8B versions. Our models establish new state-of-the-art results for their size class. Notably, MMFineReason-4B succesfully surpasses Qwen3-VL-8B-Thinking, and MMFineReason-8B even outperforms Qwen3-VL-30B-A3B-Thinking while approaching Qwen3-VL-32B-Thinking, demonstrating remarkable parameter efficiency. Crucially, we uncover a "less is more" phenomenon via our difficulty-aware filtering strategy: a subset of just 7\% (123K samples) achieves performance comparable to the full dataset. Notably, we reveal a synergistic effect where reasoning-oriented data composition simultaneously boosts general capabilities.

The development of large vision language models drives the demand for managing, and applying massive amounts of multimodal data, making OCR technology, which extracts information from visual images, increasingly popular. However, existing OCR methods primarily focus on recognizing text elements from images or scanned documents (Text-centric OCR), neglecting the identification of visual elements from visually information-dense image sources (Vision-centric OCR), such as charts, web pages and science plots. In reality, these visually information-dense images are widespread on the internet and have significant real-world application value, such as data visualization and web page analysis. In this technical report, we propose OCRVerse, the first holistic OCR method in end-to-end manner that enables unified text-centric OCR and vision-centric OCR. To this end, we constructe comprehensive data engineering to cover a wide range of text-centric documents, such as newspapers, magazines and books, as well as vision-centric rendered composites, including charts, web pages and scientific plots. Moreover, we propose a two-stage SFT-RL multi-domain training method for OCRVerse. SFT directly mixes cross-domain data to train and establish initial domain knowledge, while RL focuses on designing personalized reward strategies for the characteristics of each domain. Specifically, since different domains require various output formats and expected outputs, we provide sufficient flexibility in the RL stage to customize flexible reward signals for each domain, thereby improving cross-domain fusion and avoiding data conflicts. Experimental results demonstrate the effectiveness of OCRVerse, achieving competitive results across text-centric and vision-centric data types, even comparable to large-scale open-source and closed-source models.

Large language models allocate uniform computation across all tokens, ignoring that some sequences are trivially predictable while others require deep reasoning. We introduce ConceptMoE, which dynamically merges semantically similar tokens into concept representations, performing implicit token-level compute allocation. A learnable chunk module identifies optimal boundaries by measuring inter-token similarity, compressing sequences by a target ratio R before they enter the compute-intensive concept model. Crucially, the MoE architecture enables controlled evaluation: we reallocate saved computation to match baseline activated FLOPs (excluding attention map computation) and total parameters, isolating genuine architectural benefits. Under these conditions, ConceptMoE consistently outperforms standard MoE across language and vision-language tasks, achieving +0.9 points on language pretraining, +2.3 points on long context understanding, and +0.6 points on multimodal benchmarks. When converting pretrained MoE during continual training with layer looping, gains reach +5.5 points, demonstrating practical applicability. Beyond performance, ConceptMoE reduces attention computation by up to R^2times and KV cache by Rtimes. At R=2, empirical measurements show prefill speedups reaching 175\% and decoding speedups up to 117\% on long sequences. The minimal architectural modifications enable straightforward integration into existing MoE, demonstrating that adaptive concept-level processing fundamentally improves both effectiveness and efficiency of large language models.

In this report, we introduce Qwen3-ASR family, which includes two powerful all-in-one speech recognition models and a novel non-autoregressive speech forced alignment model. Qwen3-ASR-1.7B and Qwen3-ASR-0.6B are ASR models that support language identification and ASR for 52 languages and dialects. Both of them leverage large-scale speech training data and the strong audio understanding ability of their foundation model Qwen3-Omni. We conduct comprehensive internal evaluation besides the open-sourced benchmarks as ASR models might differ little on open-sourced benchmark scores but exhibit significant quality differences in real-world scenarios. The experiments reveal that the 1.7B version achieves SOTA performance among open-sourced ASR models and is competitive with the strongest proprietary APIs while the 0.6B version offers the best accuracy-efficiency trade-off. Qwen3-ASR-0.6B can achieve an average TTFT as low as 92ms and transcribe 2000 seconds speech in 1 second at a concurrency of 128. Qwen3-ForcedAligner-0.6B is an LLM based NAR timestamp predictor that is able to align text-speech pairs in 11 languages. Timestamp accuracy experiments show that the proposed model outperforms the three strongest force alignment models and takes more advantages in efficiency and versatility. To further accelerate the community research of ASR and audio understanding, we release these models under the Apache 2.0 license.

Streaming reconstruction from monocular image sequences remains challenging, as existing methods typically favor either high-quality rendering or accurate geometry, but rarely both. We present PLANING, an efficient on-the-fly reconstruction framework built on a hybrid representation that loosely couples explicit geometric primitives with neural Gaussians, enabling geometry and appearance to be modeled in a decoupled manner. This decoupling supports an online initialization and optimization strategy that separates geometry and appearance updates, yielding stable streaming reconstruction with substantially reduced structural redundancy. PLANING improves dense mesh Chamfer-L2 by 18.52% over PGSR, surpasses ARTDECO by 1.31 dB PSNR, and reconstructs ScanNetV2 scenes in under 100 seconds, over 5x faster than 2D Gaussian Splatting, while matching the quality of offline per-scene optimization. Beyond reconstruction quality, the structural clarity and computational efficiency of \modelname~make it well suited for a broad range of downstream applications, such as enabling large-scale scene modeling and simulation-ready environments for embodied AI. Project page: https://city-super.github.io/PLANING/ .

Agentic Reinforcement Learning (Agentic RL) has achieved notable success in enabling agents to perform complex reasoning and tool use. However, most methods still relies on sparse outcome-based reward for training. Such feedback fails to differentiate intermediate reasoning quality, leading to suboptimal training results. In this paper, we introduce Agent Reasoning Reward Model (Agent-RRM), a multi-faceted reward model that produces structured feedback for agentic trajectories, including (1) an explicit reasoning trace , (2) a focused critique that provides refinement guidance by highlighting reasoning flaws, and (3) an overall score that evaluates process performance. Leveraging these signals, we systematically investigate three integration strategies: Reagent-C (text-augmented refinement), Reagent-R (reward-augmented guidance), and Reagent-U (unified feedback integration). Extensive evaluations across 12 diverse benchmarks demonstrate that Reagent-U yields substantial performance leaps, achieving 43.7% on GAIA and 46.2% on WebWalkerQA, validating the effectiveness of our reasoning reward model and training schemes. Code, models, and datasets are all released to facilitate future research.

The evolution of Large Language Models (LLMs) into autonomous agents necessitates the management of extensive, dynamic contexts. Current benchmarks, however, remain largely static, relying on passive retrieval tasks that fail to simulate the complexities of agent-environment interaction, such as non-linear reasoning and iterative feedback. To address this, we introduce AgentLongBench, which evaluates agents through simulated environment rollouts based on Lateral Thinking Puzzles. This framework generates rigorous interaction trajectories across knowledge-intensive and knowledge-free scenarios. Experiments with state-of-the-art models and memory systems (32K to 4M tokens) expose a critical weakness: while adept at static retrieval, agents struggle with the dynamic information synthesis essential for workflows. Our analysis indicates that this degradation is driven by the minimum number of tokens required to resolve a query. This factor explains why the high information density inherent in massive tool responses poses a significantly greater challenge than the memory fragmentation typical of long-turn dialogues.

Electroencephalography (EEG) foundation models have recently emerged as a promising paradigm for brain-computer interfaces (BCIs), aiming to learn transferable neural representations from large-scale heterogeneous recordings. Despite rapid progresses, there lacks fair and comprehensive comparisons of existing EEG foundation models, due to inconsistent pre-training objectives, preprocessing choices, and downstream evaluation protocols. This paper fills this gap. We first review 50 representative models and organize their design choices into a unified taxonomic framework including data standardization, model architectures, and self-supervised pre-training strategies. We then evaluate 12 open-source foundation models and competitive specialist baselines across 13 EEG datasets spanning nine BCI paradigms. Emphasizing real-world deployments, we consider both cross-subject generalization under a leave-one-subject-out protocol and rapid calibration under a within-subject few-shot setting. We further compare full-parameter fine-tuning with linear probing to assess the transferability of pre-trained representations, and examine the relationship between model scale and downstream performance. Our results indicate that: 1) linear probing is frequently insufficient; 2) specialist models trained from scratch remain competitive across many tasks; and, 3) larger foundation models do not necessarily yield better generalization performance under current data regimes and training practices.

Current approaches to reducing undesired capabilities in language models are largely post hoc, and can thus be easily bypassed by adversaries. A natural alternative is to shape capabilities during pretraining itself. On the proxy task of removing medical capabilities, we show that the simple intervention of filtering pretraining data is highly effective, robust, and inexpensive at scale. Inspired by work on data attribution, we show that filtering tokens is more effective than filtering documents, achieving the same hit to undesired capabilities at a lower cost to benign ones. Training models spanning two orders of magnitude, we then demonstrate that filtering gets more effective with scale: for our largest models, token filtering leads to a 7000x compute slowdown on the forget domain. We also show that models trained with token filtering can still be aligned on the forget domain. Along the way, we introduce a methodology for labeling tokens with sparse autoencoders and distilling cheap, high-quality classifiers. We also demonstrate that filtering can be robust to noisy labels with sufficient pretraining compute.

Public repositories host millions of fine-tuned models, yet community usage remains disproportionately concentrated on a small number of foundation checkpoints. We investigate whether this concentration reflects efficient market selection or if superior models are systematically overlooked. Through an extensive evaluation of over 2,000 models, we show the prevalence of "hidden gems", unpopular fine-tunes that significantly outperform their popular counterparts. Notably, within the Llama-3.1-8B family, we find rarely downloaded checkpoints that improve math performance from 83.2% to 96.0% without increasing inference costs. However, discovering these models through exhaustive evaluation of every uploaded model is computationally infeasible. We therefore formulate model discovery as a Multi-Armed Bandit problem and accelerate the Sequential Halving search algorithm by using shared query sets and aggressive elimination schedules. Our method retrieves top models with as few as 50 queries per candidate, accelerating discovery by over 50x.

Recent research in long-form video generation has shifted from bidirectional to autoregressive models, yet these methods commonly suffer from error accumulation and a loss of long-term coherence. While attention sink frames have been introduced to mitigate this performance decay, they often induce a critical failure mode we term sink-collapse: the generated content repeatedly reverts to the sink frame, resulting in abrupt scene resets and cyclic motion patterns. Our analysis reveals that sink-collapse originates from an inherent conflict between the periodic structure of Rotary Position Embedding (RoPE) and the multi-head attention mechanisms prevalent in current generative models. To address it, we propose a lightweight, training-free approach that effectively suppresses this behavior by introducing multi-head RoPE jitter that breaks inter-head attention homogenization and mitigates long-horizon collapse. Extensive experiments show that our method successfully alleviates sink-collapse while preserving generation quality. To the best of our knowledge, this work achieves the first demonstration of real-time, streaming, and infinite-length video generation with little quality decay. As an illustration of this robustness, we generate continuous videos up to 12 hours in length, which, to our knowledge, is among the longest publicly demonstrated results in streaming video generation.

European Open Source Academy 的 2025 年开源卓越奖得主、cURL 维护者 Daniel Stenberg 宣布了 2026 年的开源卓越奖得主、稳定版 Linux 内核维护者 Greg Kroah-Hartman。他表示：很难夸大 Greg 在 Linux 上的工作的重要性。在软件领域，创新总能抢占头条，但稳定性却默默守护着生命和生计。每一部 Android 手机、每一台 Web 服务器、每一个运行 Linux 的关键系统，都依赖于 Greg 精益求精的工作。正因为他的努力，医院、银行、政府和个人在使用 Linux 时，才能安心无忧。他的工作代表着最高形式的服务：不求浮华，坚持不懈，却不可或缺。

CERN 获得 10 亿美元私人捐赠用于建造未来环形对撞机（Future Circular Collider，FCC），这是该机构 72 年历史上首次有私人和慈善基金支持其大型项目。FCC 有望成为大强子对撞机（LHC）的继任者。FCC 设计建造一条长约 90.7 公里的巨型隧道——其长度三倍于 LHC——平均深度约为地下 200 米。FCC 方案是 CERN 下一代对撞机的首选方案，将于 2026 年 5 月递交给 CERN 理事会，如果理事会在 2028 年批准该方案，那么 FCC 电子正电子对撞机（FCC-ee）的建造将于 2030 年启动，2047 年投入运行。

负责评选诺贝尔和平奖的挪威诺贝尔研究所在安全部门帮助下完成了内部调查，证实遭到了黑客入侵。2025 年诺贝尔和平奖得主、委内瑞拉反对派领导人 Maria Corina Machado 的名字提前泄露可能是黑客攻击所致。在去年 10 月 Machado 的名字公开前几小时，预测平台 Polymarket 上有关她的投注激增，她此前并不被认为是和平奖的热门人选。

GNU 国际化与本地化函数库 gettext 在历经逾 30 年开发之后终于释出了具有象征意义的 1.0 版本。gettext 主要优势是将编程和翻译分开。GNU gettext 1.0 的主要变化包括：改进 PO(Portable Object)文件处理，新 po-fetch 程序从网上的翻译项目提取已翻译的 PO 文件，新预翻译程序 msgpre 和 spit，改进 Ocaml 和 Rust语言支持；等等。msgpre 和 spit 可通过本地安装的大模型去实现机器翻译，msgpre 应用于整个 PO 文件，而 spit 则是单则信息。

以隐私为卖点的搜索引擎 DuckDuckGo 调查了其用户对 AI 功能的态度，结果显示用户压倒性多数的反对 AI：在 175,354 名参与投票的用户中，九成用户表示不希望使用 AI。DuckDuckGo 为此推出了两个版本：反 AI 用户可选择访问 noai.duckduckgo.com，想要 AI 功能的用户可访问 yesai.duckduckgo.com。用户还可以在主站设置中禁用 AI 摘要、AI 生成图像以及 Duck.ai 聊天机器人。

YouTube 证实调整了平台体验，阻止非付费用户访问后台播放功能。在确认前，三星浏览器 Samsung Internet、Brave、Vivaldi 甚至 Microsoft Edge 用户通过社交网络报告后台视频播放功能失效。后台视频播放对移动用户而言是一项有用且方便的功能，用户可以在关闭手机屏幕或最小化浏览器窗口的情况下听视频的声音，YouTube 上有很多适合听的内容，如音乐和播客。但从一周前开始，用户报告关闭手机屏幕或最小化浏览器窗口后音频播放停止了。YouTube 官方证实这是有意为之，称后台播放功能只提供给付费订阅用户。

根据发表在《Scientific Reports》期刊上的一项研究，虽然海冰面积减少但挪威 Svalbard 群岛上的北极熊却更胖更健康。北极熊以海冰为平台捕猎海豹，海豹是其获取富含脂肪食物的主要来源。脂肪储备提供了能量和保暖，让母熊能分泌乳汁哺育幼崽。研究人员分析了 1992-2019 年间 Svalbard 群岛捕获的 770 只成年北极熊的身体状况，发现它们明显变胖了。研究人员认为群岛上的北极熊通过捕食更多驯鹿和海象在内的陆地猎物去适应海冰面积的减少。研究期间全球气温上升使该地区每年的无冰天数增加了近 100 天——平均每年增加约 4 天。研究人员认为这种情况不太可能长期持续下去，随着海冰持续减少，北极熊将不得不跋涉更远的距离抵达猎场，它们将会消耗掉更多宝贵的脂肪储备。

去年引发广泛关注的小行星 2024 YR4 已被认为不太可能会撞击地球，但有 4% 的概率会在 2032 年 12 月 22 日撞击月球。2024 YR4 直径约为 60 米，如果它撞上月球，产生的能量相当于一枚中型热核武器。撞击将使月球亮起一个肉眼可见的光点，届时处于夜晚侧的太平洋地区居民，将能目睹这一幕。撞击会留下一个直径约 1 公里，深度达 200 米左右的陨石坑，中心还会有一池直径 100 米的熔岩，韦伯太空望远镜（JWST）可以借此观察月球岩石冷却与坑洞形成的过程。这次冲击预计会引发里氏规模 5.0 的全月球地震，透过地震波在月球内部的传导，科学家能了解月球内部的构造。撞击会喷发出大量碎片，科学家预计约有 400 公斤的月球岩石会掉进地球大气层，这基本上等同于一次免费的月球采样返回任务。此外 2032 年的圣诞期间将出现历史上最壮观的流星雨，模拟显示，在地球的某些地区，每小时的天顶流星率将超过 2000 万，其中亦包括每小时 100 至 400 颗的超亮火流星，就连过往历史纪录中的狮子座流星雨都相形见绌。然而这场流星秀的代价可能相当高昂，大量喷发的碎片可能会撞击轨道卫星并引发连锁反应，形成凯斯勒现象：碎裂的卫星产生更多碎片，进而毁掉全球的导航、网络系统，甚至让我们在未来几十年内都无法安全地将任何太空船送入轨道。

Global Energy Monitor(GEM)报告，AI 数据中心驱动美国天然气发电量大幅增长，导致温室气体排放也随之大幅上升。今年全球新增天然气发电装机容将打破年度纪录，在建项目将使全球现有天然气发电装机容量增长近 50%。美国是领导头，在建 252 GW 装机容量三分之一靠近数据中心。如果全部建成，这些天然气发电站生命周期内将产生 121 亿吨二氧化碳，是美国目前所有能源年排放量的两倍。

根据发表在《科学》期刊上的一项研究，人类寿命的遗传性远高于以往的认知。分析显示，在排除了诸如意外事故或传染病等外部因素所导致的死亡之后，遗传因素或许可解释影响人类寿命长短中的约 50%的。理解人类寿命的遗传性是衰老问题研究的核心，然而要衡量基因对长寿的影响仍颇为棘手。尽管已发现一些与寿命相关的基因，但外部环境因素——如疾病或生活条件——对个体寿命的长短影响重大，因而常会掩盖或模糊潜在的遗传影响。为厘清死亡的内、外成因，研究人员运用了数学模型、人类死亡率模拟以及多个大规模双胞胎队列数据集。研究结果显示，外源性死亡会系统性地压低对寿命遗传影响的估测。一旦将外因导致的死亡数据进行妥善剥离，作者发现，遗传对人类寿命的影响率会大幅跃升至 55% 左右——这一数值是先前估计的两倍以上，表明遗传是决定人类衰老进程的核心驱动因素。