论文

尽管聚合准确率有所提升，但视觉工具使用在广泛的 rollout 中并不具备因果有效性。Despite aggregate accuracy gains, visual tool-use is not causally effective across a broad range of rollouts: despite aggregate accuracy gains, visual tool-use is not causally effective across a broad range of rollouts.

本文提出进化式马尔可夫超图攻击（EMHA），这是一种黑盒策略，通过协调授权状态转移执行反馈驱动的环境演化，无需参数更新，并将 OpenART 确立为在复杂演化环境中研究 Agent 安全性的可扩展基础。This work proposes the Evolutionary Markov Hypergraph Attack (EMHA), a black-box policy that performs feedback-driven environment evolution by coordinating authorized state transitions without requiring parameter updates, and establishes OpenART as a scalable foundation for studying agent safety in complex, evolving environments.

Mechanist 是一个 Agentic 系统，将 AI 作为科学仪器用于自主发现 AI 智能背后的机制，并发展了关于 belief 的机制理论，揭示了模型如何表征世界知识、形成 belief、推断他人 belief，以及这些机制如何在预训练过程中涌现。Mechanist is an agentic system that uses AI as a scientific instrument for the autonomous discovery of mechanisms underlying AI intelligence, and develops a mechanism theory of belief, revealing how models represent world knowledge, form beliefs, infer the beliefs of others, and how these mechanisms emerge during pretraining.

两项研究为 GPU Agent 控制建立了两个可度量的门槛：deadline 可达的 cohort 供给与观测放置，并使用固定分区份额 F、精确离线份额 P*、局部上界 U 和在线达成份额 A 对 ready-cohort 边界进行了形式化。Two studies establish two measurable gates for GPU agent control: deadline-feasible cohort supply and observation placement and formalize the ready-cohort boundary using fixed-partition share F, exact offline share P*, local upper bound U, and online achieved share A.

本文提出 SHAPER，一种免训练具身自适应的自演化框架，保持模型参数冻结，通过目标环境 rollout 演化可复用的 skills 和 context-code harness 来改进非参数化 Agent 系统。This work proposes SHAPER, a self-evolving framework for train-free embodied adaptation that keeps model parameters frozen and improves the non-parametric agent system by evolving reusable skills and a context-code harness through target-environment rollouts.

本文提出 SkillZip，一种执行感知的程序化抽象框架，对 section 级图执行保持契约的压缩，加载一个紧凑、依赖闭合的 context，并仅在需要时展开宏。SkillZip is proposed, an execution-aware procedural abstraction framework that performs contract-preserving compression over section-level graphs that hydrates a compact, dependency-closed context and expands macros only when required.

本工作综述了可用于推断用户需求的贝叶斯用户模型研究，这些模型综合考虑用户的背景、操作和查询，并提出了一种智能用户界面的整体架构。This work reviews work on Bayesian user models that can be employed to infer a user's needs by considering a users' background, actions, and queries and proposes an overall architecture for an intelligent user interface.

探索以交错方式使用 LLM 同时生成推理轨迹和任务特定动作，使两者产生更大协同：推理轨迹帮助模型归纳、跟踪和更新动作计划以及处理异常，而动作使其与外部源交互以获取额外信息。The use of LLMs are explored to generate both reasoning traces and task-specific actions in an interleaved manner, allowing for greater synergy between the two: reasoning traces help the model induce, track, and update action plans as well as handle exceptions, while actions allow it to interface with external sources to gather additional information.

SKILLER 是一个由自然语言驱动的强化学习框架，旨在为小模型自动生成执行器特定的 skills，使用强模型作为 actor 和 critic，将小模型 Agent 系统视为环境，并通过自然语言完全传递所有强化学习信号。SKILLER is a natural-language-driven reinforcement learning framework designed to automatically generate executor-specific skills for small models, which employs a strong model as the actor and critic, treats the small-model agent system as the environment, and propagates all reinforcement learning signals entirely via natural language.

提出 Agentic Video Auto-Encoder（AVA-Encoder），一种由 agentic 自我进化驱动的新型自编码框架，用于学习 agent-native 视频表示，在 shot-level 和 keyframe-level system-prompt token 使用量减少 74.3% 的同时，性能优于精心人工调优的策略。The Agentic Video Auto-Encoder (AVA-Encoder), a novel auto-encoding framework driven by agentic self-evolution to learn agent-native video representations that outperforms a carefully human-tuned policy while using 74.3% fewer shot-level and keyframe-level system-prompt tokens.

本文报告了一项完整的、有完整记录的案例研究：在规范优先协议下，由 AI 编码 Agent 对大规模架构进行重构，期间无人工代码审查、无预先存在的预言机来验证目标行为。该任务是在一个大型相互依赖的代码库中拆除核心不变量，作者评估认为通过增量重构基本上不可行，这类变更通常需要重写。本文所述协议下，Agent 成功完成了任务。该系统包含 717,725 行This paper reports a single, fully instrumented case study of a large-scale architectural refactoring by an AI coding agent under a specification-first protocol, with no human review of the generated code and no pre-existing oracle to validate the target behaviour. The task, dismantling a central invariant across a large interdependent codebase, was assessed by the author as effectively infeasible through incremental refactoring, the kind of change that conventionally calls for a rewrite instead. Under the protocol described here, the agent completed it successfully. The system is a 717,725-li

提出 Second Thought，一种免训练的推理框架，在每个 Thought 阶段结束时立即 fork 四个辅助分支，与主循环并发解码，并在环境 observation 到达时将生成的 thought 合并回去。This work proposes Second Thought, a training-free inference framework that forks four auxiliary branches the instant each Thought phase concludes, decodes them concurrently with the main loop, and merges the generated thoughts back when the environment observation arrives.

提出 Latent On-Policy Self-Distillation（LOPD），不再提出另一种手工设计、附带新形式 privileged context 的 OPSD 变体，而是让 teacher 的 privileged context 本身可从经验端到端学习。This work introduces Latent On-Policy Self-Distillation (LOPD), which, rather than proposing another hand-crafted OPSD variant with a newly prescribed form of privileged context, makes the teacher's privileged context itself learnable end-to-end from experience.

提出一种 chunked-prefill 策略，可缓解由此带来的内存容量惩罚，在 32 GiB 共享内存上将允许的上下文宽度扩展 $2.7 \times$，但即便降低了内存开销，仍需打补丁才能使 Nanbeige4.2-3B 可用。A chunked-prefill strategy is introduced which alleviates the incurred memory-capacity penalty, extending allowable context width by $2.7 \times$ on 32~GiB shared memory, however, even with the reduced memory overhead, it is shown that patches are required to render Nanbeige4.2-3B usable.

探讨共享工作空间上 LLM Agent 委员会的审议过程是否能被捷径和线索（benchmark 所奖励但临床医生会忽略的）所博弈，以及委员会的社会可信度所构成的游戏。It is asked whether committees of language-model agents deliberating on a shared workspace can be gamed by shortcuts, cues a benchmark rewards but a clinician would ignore, and what games a committee is social plausibility.