Crypto & Web3

Agent decisions depend on empirical relationships that deployment observations reveal and task descriptions alone may leave unresolved. We introduce Decoupled Predictive Decision Making (DPDM), an architecture that formulates heterogeneous agent decisions as conditional prediction with a shared pretrained learner. Language models provide semantic representations of current and historical records, while a general-purpose conditional predictor predicts task-defined targets from the represented evidence. Pretraining supplies reusable inference capability; deployment evidence instantiates problem-specific predictions without updating either model's neural parameters. Tool judgments, candidate preferences, and reasoning assessments share an evidence-and-query interface, with predictions mapped to choices by a decision rule. This architecture establishes complementary sources of agent capability: semantic knowledge acquired through language pretraining and empirical inference acquired through structured-data pretraining. A single frozen LimiX-2 predictor serves all five task categories. With Qwen3.5-27B as the semantic encoder, DPDM raises mean accuracy across 50 benchmarks from 78.80% with few-shot prompting to 84.92% under their respective evaluated history budgets, and reaches 82.33% with identical histories and queries. On ToolPRMBench's BFCL and ToolSandbox tasks, absolute accuracy gains are 34.26% and 28.87%, respectively, at the methods' respective evaluated history budgets. Accuracy improves as history grows. With identical imbalanced histories, mean balanced accuracy improves by an absolute 14.51% across five reasoning-step assessment tasks and four encoders. DPDM makes learning from experience an independently improvable foundation-model capability, creating a shared route for advances in conditional prediction to improve decisions across agent tasks.

Progress toward artificial general intelligence (AGI) has largely relied on scaling a resource-intensive executive, System-2, through larger models, more data and compute, longer reasoning, and more agents. We ask whether the next stage may come instead from co-designing it with System-1, a lightweight, semantically aware predictor that evaluates candidate interactions before execution, so that System-2 acts only on those worth their cost. Our answer is a qualified yes. We study conditional interaction, a predict--gate--execute--update loop: System-1 estimates each candidate's utility, System-2 executes those admitted by an adaptive threshold, and the outcomes update System-1. The loop spans training, test-time reasoning, adaptive decision-making, and agentic tool use, with utility and cost defined by the application. Under ideal screening and equal execution costs, execution compute falls by a factor approaching 1/ρ_u, where ρ_u is the density of utility-relevant interactions (cost-weighted when costs differ); prediction errors, exploration, and distribution shift reduce the saving. We bound selection regret by predictor error and the utility margin. These results motivate our central hypothesis: ρ_u is a measurable coordinate of scaling efficiency and makes informative compute a better description of scaling than total compute.

Recent advances in video world models have enabled the generation of increasingly realistic and interactive virtual environments, opening new possibilities for player-customizable gameplay. Agentic frameworks further advance this direction by decoupling explicit game logic and controllable world representations from visual generation. However, existing approaches support only simple game settings and predefined motion patterns, generalize poorly to unseen environments and characters, and offer limited real-time interactivity. In this paper, we introduce Wizard, an agentic game world model that enables real-time, precise control over character motions while generalizing zero-shot across novel scenes, characters, and actions. To achieve this, we construct a diverse dataset spanning 750 scenes and 178 characters, incorporating skeleton and geometry information as structured representations. We leverage these representations as intermediate proxies to condition a video generation model, together with an adaptive masking mechanism that improves alignment between the conditioning signals and generated video rollouts. Furthermore, we introduce an agentic framework that explicitly maintains and updates game states, allowing players to freely configure their virtual worlds and exercise fine-grained control over character motions while preserving visual quality and gameplay consistency. By combining agentic control with structured proxy-based generation, our framework unlocks new possibilities for player-driven game creation with real-time, generalizable, and mechanically consistent world simulation.

The hair of stylized characters in games and avatars is built from hair cards: artist-placed ribbons whose geometry is the visible hair, animated by spring bones. Existing image-based methods produce realistic hair or a single fused mesh, while CHARM, the only generator of stylized hair cards, decodes a hairstyle autoregressively as a long sequence of control points. Observing that a card hairstyle is an unordered set of artist-defined primitives, we propose HairDeck, which generates it as one: each card is a single token, and a set diffusion transformer denoises all cards together. From a single image, HairDeck generates the cards and the spring-bone chains that drive them, yielding an animatable asset that exports to ready-to-use downstream formats. On CHARM's own test set, it lowers Chamfer distance by 44% and card-orientation error by more than half while running 33 times faster, and from single images it outperforms CHARM, image-to-3D pipelines and strand-based methods. Project page: https://hyzcluster.github.io/HairDeck

Multi-agent systems often rely on predefined collaboration structures, limiting their ability to adapt to diverse task requirements. We introduce DynaFlow, a framework that integrates free-form executable workflow synthesis into the action space of the main agent. The agent decides when collaboration is needed and generates task-specific programs that coordinate sub-agents through sequential or parallel execution, structured information exchange, and verification. Execution results and traces inform subsequent actions, enabling the agent to adapt collaboration as reasoning progresses. We train only the main agent through supervised fine-tuning on distilled trajectories, followed by refinement on examples filtered for unsupported premises, biased verification, and information-flow defects. All sub-agents remain fixed, separating orchestration learning from executor capability improvement. Across six benchmarks spanning mathematical reasoning, scientific question answering, and multi-hop retrieval, DynaFlow achieves 88.08% overall accuracy in Forced mode, outperforming the strongest evaluated baseline by 10.90 percentage points with the same Qwen3.5-27B backbone. Workflow analysis finds more explicit use, verification, and refinement of upstream outputs after training, highlighting cross-stage information flow as a key dimension of multi-agent orchestration.

Rubric-based rewards enable effective reinforcement learning on non-verifiable tasks. However, because these rewards are typically defined as a weighted measure of rubric coverage, models are trained primarily to maximize a recall objective. As a result, RL-trained models produce responses that are more complete but also more verbose and contain more unnecessary or factually incorrect content, leading them to be less preferred than responses from the base model. To address this issue, we present the FORK reward, which jointly optimizes recall and a novel precision objective, which requires each unit of a model response to be both necessary and factually correct, as measured by rubric-driven necessity credits and a factual-correctness grader, respectively. Our experimental results show that FORK outperforms existing rubric-based RL methods and achieves Pareto-optimal performance that balances rubric coverage and overall response quality. Compared to the original recall-based reward, FORK substantially improves precision and reduces response length while achieving similar rubric coverage, which leads to significantly higher win rate compared to the base policy (e.g., from 10.6% to 68.0% on RubricHub-Medical and from 22.1% to 74.1% on HealthBench).

Building virtual embodied agents that operate in open-ended games like human players is a long-standing goal requiring both long-horizon autonomy and reliable native-interface control. As a procedurally generated open world, Minecraft provides a natural testbed for studying the integration of these capabilities. Existing agents typically provide either native visuomotor control without long-horizon autonomy or high-level planning executed through environment APIs or predefined skills. To bridge this gap, we propose HiSTEVE, a hierarchical VLA agent with a capability-aware agent harness. At the orchestration level, we equip the harness with structured memory for tracking progress and a VLM planner for selecting subtasks within the VLA's capabilities. To reliably determine subtask completion, we further introduce a policy-coupled task completion state detector that conditions on VLA policy context to signal candidate completion. At the control level, a single VLA executes all subtasks with vision-only perception and native keyboard-and-mouse actions. To mitigate interference between heterogeneous GUI and non-GUI interactions, we introduce regime-specific RMSNorm branches and separate mouse-movement token embeddings. We also train the VLA through world knowledge injection, imitation learning, and reinforcement learning with environment feedback to improve reliability and recovery. HiSTEVE achieves state-of-the-art atomic-task performance, scoring 85.0% on MineStudio Bench and a 37.4% average success rate on OpenHA, while also completing long-horizon tasks such as crafting an iron pickaxe from scratch like human players.

Anthropic : Anthropic releases FlashProve, an open-source prototype that cryptographically verifies an AI response came from a given model, not one that a router swapped in —  Roy Rinberg (Anthropic), Alex Allain (Anthropic); Alessandro Chiesa (EPFL, StarkWare), Miranda Christ (MIT, RESI), Rahul Dalal …

Jason Shubnell / The Block : Brazil's largest crypto exchange Mercado Bitcoin halts withdrawals after a breach involving $46M+ in assets, per Arkham; Tether froze 4.5M+ USDT in response —  The exchange paused deposits and withdrawals after the incident, while Tether froze more than 4.5 million USDT linked to the attacker.

Zack Abrams / The Block : Binance says net outflows were $3.64B, or 2.1% of assets, in the 9.5 hours after it began restoring withdrawals; DefiLlama puts 24-hour net outflows at $4.05B —  The exchange said the outflows equal 2.1% of its assets and that withdrawal volumes have eased after an initial spike.

Angela Christy / Reuters : Binance says it has covered 90% of its hack losses, having set aside $6.34B+ of company funds; the remaining 10% is in less liquid tokens —  Cryptocurrency exchange Binance said on Saturday that it was able to cover 90% of the amount stolen during its recent hack.

The Commanding Heights : As AI models commoditize, lasting wealth will accrue to those controlling chokepoints like distribution, payment rails, and a stablecoin dollar, not to the labs —  Scarce, controllable positions of Economic Power whose holders durably capture the gains of Increasingly Capable and diffused intelligence.

Financial Times : Chainalysis says Binance hackers used automated money-laundering patterns not seen before; Elliptic: almost all of the $6.3B was taken in the first 30 minutes —  North Korean hackers' attack on Binance takes crypto theft to an unprecedented scale  —  The largest financial theft in history took no more than 30 minutes.

Olga Kharif / Bloomberg : Coinbase reports Q3 revenue down 35% YoY to $1.22B, in line with est., and net income up 66% to $719M, its first profit in a year, on unrealized crypto gains —  Coinbase Global Inc. returned to profitability for the first time in a year while posting a quarterly decline in revenue …

Reuters : Robinhood reports Q3 revenue up 12% YoY to $1.42B, in line with est., crypto revenue down 55% to $120M, and profit down 14% to $476M; HOOD drops 5%+ after hours —  Robinhood Markets (HOOD.O) reported a drop in third-quarter profit on Tuesday as slower cryptocurrency trading weighed on growth …

Olga Kharif / Bloomberg : Sources: Hong Kong-based stablecoin payments startup RedotPay plans a US IPO filing by year-end and is in talks for a pre-IPO round at a $4B to $5B valuation —  Crypto firm Redotpay is considering filing confidentially for a US initial public offering by year-end, according to people familiar …

在一场被称为史上规模最大的加密货币窃案中，黑客仅用 20 分钟就从币安盗取了价值 63 亿美元的加密货币。币安随后暂停了提款和提现。约一半的被盗资金——全部是稳定币，稳定币发行方能通过智能合约冻结交易——被成功冻结，但另外一半是无法被冻结的比特币、以太币和 XRP，可能难以追回了，币安的损失可能超过 30 亿美元。加密货币追踪公司 TRM Labs 的分析显示，币安在以太坊、比特币、波场和 Solana 等 10 个区块链上的钱包全部被清空，资金转移到了攻击者控制了多个钱包。攻击者的准备工作至少在窃案发生前 36 小时就开始了。攻击者在实施入侵前在多个钱包上测试了攻击代码。测试后四个小时将攻击代码植入到币安的一个热钱包。攻击者被认为是 TraderTraitor——该组织此前曾从 Bybit 交易所窃取了价值 15 亿美元的加密货币。币安称攻击者可能是从一名工程师的笔记本电脑开始的。