论文

将 Agent-Centric Interactive World Proxies 概念化，将基础范式从物理状态转移转向 agent 可用的信息转移，如执行结果、检索到的经验或技能、以及验证信号，扩展了世界建模的范围，为持续改进的 agent 提供多样化反馈。This work conceptualize Agent-Centric Interactive World Proxies, shifting the fundamental paradigm from physical state transitions to agent-usable information transitions, such as execution outcomes, retrieved experiences or skills, and verification signals, broadening the scope of world modeling to provide versatile feedback for continually improving agents.

高粘度污渍以其高粘度与复杂流变特性，仍是机器人表面清洁的主要挑战。传统擦拭往往扩散污渍，而擦洗摩擦力更强却存在损伤表面的风险。本文提出 Push-Wiper，一种将高粘度污渍清洁重构为聚集问题的框架。Push-Wiper 使用海绵通过分段推送轨迹渐进式聚集污渍，随后通过后处理阶段剥离已聚集物质并实现海绵自清洁。我们采用逐步Viscous stains, characterized by high viscosity and complex rheological properties, remain a major challenge for robotic surface cleaning. Conventional wiping often spreads the stain, while scrubbing provides stronger friction but risks damaging the surface. In this paper, we propose Push-Wiper, a framework that reformulates viscous stain cleaning as an aggregation problem. Push-Wiper employs a sponge to progressively gather stains through segmented pushing trajectories, followed by a post-processing phase that detaches the aggregated material and enables sponge self-cleaning. We adopt a stepw

提出 ContinualSkillBench，一个面向 in-context 持续 skill 学习的动态评估框架，表明当前 in-context skill 进化机制能够支持持续适应，但仍难以稳定地将经验整合为鲁棒且可迁移的 skill。ContinualSkillBench is introduced, a dynamic evaluation framework for in-context continual skill learning that shows that current in-context skill evolution mechanisms can support continual adaptation, but still struggle to consistently consolidate experience into robust and transferable skills.

PosterMELD 是一个模板条件的多 agent 流水线：capacity-aware slot 在渲染前引导写作，确定性 gate 与 VLM 审核将失败路由到有界修复，在生成的多种方法中获得最高的条件 CHE 并产出多个可印刷输出。PosterMELD is a template-conditioned multi-agent pipeline: capacity-aware slots guide writing before rendering, and deterministic gates plus vision-language model (VLM) review route failures to bounded repair result in the highest conditional CHE among generated methods with multiple print-ready outputs.

提出 Answer-Backtracked Credit Assignment（ABC），一种面向长程搜索 agent 训练的细粒度信用分配框架，将稀疏的轨迹级结果转换为稠密的步骤级监督，对有用动作（即使在失败轨迹中）给予奖励，同时抑制错误或冗余动作。Answer-Backtracked Credit Assignment (ABC) is proposed, a fine-grained credit assignment framework for training long-horizon search agents by converting sparse trajectory-level outcomes into dense step-level supervision that rewards useful actions (even in failed trajectories) while suppressing erroneous or redundant actions.

提出 FocusMem，在紧凑的潜空间记忆接口中分离情景记忆与工作记忆，一致优于完全匹配的动作-only 固定记忆基线以及先前的潜空间记忆适配方法。FocusMem is introduced, which separates episodic memory and working memory within a compact latent-memory interface and consistently outperforms a fully matched action-only fixed-memory baseline and prior latent memory adaptations.

开发 PIMiner，一种用于 prompt injection 红队的 agentic 系统，可在训练阶段从零构建策略库，并在测试时无需额外训练直接迁移到未见过的目标 LLM。PIMiner is developed, an agentic system for prompt injection red-teaming that builds a strategy library from scratch during training and can be directly transferred to a previously unseen target LLM without additional training at test time.

提出一种用于符号音乐的分层自监督"世界模型"，采用 2.55M 参数的 Swin V2 编码器，在 MIDI 钢琴卷帘图像上以 JEPA 风格目标（音高与时间平移等变性、掩码嵌入预测以及分布正则化）训练，无需标签与乐理词汇。A hierarchical self-supervised ``world model'' for symbolic music is presented, using a 2.55M-parameter Swin V2 encoder trained on MIDI piano-roll images with JEPA-style objectives (pitch- and time-shift equivariance, masked embedding prediction, and a distributional regularizer), using no labels and no music-theory vocabulary.

EnvACE 是一种 Agentic 强化学习方法，用 world rehearsal 替代训练中的外部环境交互，将 world rehearsal 确立为突破外部环境约束、扩展 LLM Agent 训练的新路径。EnvACE is introduced, an agentic reinforcement learning method that replaces external environment interaction during training with world rehearsal, establishing world rehearsal as a new path toward scaling LLM agent training beyond the constraints of external environments.

CalibForge 是一个面向终端任务的自动合成系统，利用已验证的求解器行为，通过对抗式求解器校准来修订候选任务；消融实验表明，两种策略都比仅靠人工撰写加验证、或普通单求解器反馈产生更有效的监督信号。CalibForge is presented, an autonomous terminal-task synthesis system that uses verified solver behavior to revise candidate tasks through adversarial solver calibration and ablations show that both strategies yield more effective supervision than authoring and validation alone or ordinary single-solver feedback.

提出构建经济世界模型（作为生成式引擎）的实施路线图：异质 Agent 在其中行动、交互、适应并与市场和制度共同演化，由此从内部生成经济动态。This paper develops an implementation roadmap for building economic world models as generative engines in which heterogeneous agents act, interact, adapt, and co-evolve with markets and institutions, thereby producing economic dynamics from the inside.

提出 ASGE-RR，一种支持可修订预留的在线 ASGE 控制器：该在线网络控制问题将运行时揭示的工作流调用映射到服务副本与网络路径上，受容量、成本和截止时间约束；研究表明，运行时揭示的工作流结构创造了新的网络控制机会。This work presents ASGE-RR, an online ASGE controller with revisable reservations, an online network-control problem that maps runtime-revealed workflow calls to service replicas and network paths under capacity, cost and deadline constraints and suggests that runtime-revealed workflow structure creates a new network control opportunity.

提出 FactorJEPA，将世界结构作为一等预测原语，并通过 visibility gate 与分离的子空间来组合布局、实体与交互，以保留部分可观测的 Agent 并抑制跨因子捷径。FactorJEPA is introduced, which makes world structure a first-class predictive primitive, and composes layout, entities, and interactions, using a visibility gate and separated subspaces to preserve partially observed agents and discourage cross-factor shortcuts.

提出 PHOENIX（Predictive Health On-orbit Edge Neural Intelligence eXtension），为卫星赋予自主故障推理能力，并在 ESA Anomaly Detection Benchmark 上报告了初步结果。PHOENIX (Predictive Health On-orbit Edge Neural Intelligence eXtension) is proposed to give the satellite its own fault reasoning capability, and preliminary results on the ESA Anomaly Detection Benchmark are reported.

SMRC-SD（State-Matched Routing and Contextualized Self-Distillation）显式地决定特权轨迹应在何时、以何种方式指导 on-policy student，其表现始终优于无条件的成功全路径蒸馏。State-Matched Routing and Contextualized Self-Distillation (SMRC-SD), which explicitly determines when and how a privileged trajectory should guide an on-policy student, consistently outperforms unconditional successful full-path distillation.

我们提出 Ouroboros，一个自进化的 Agent harness，其工具、提示、上下文组装与核心实现通过已评审的 commit 持续改进，并成为后续工作的运行时。核心演化以两种模式推进：在递归自由演化中，改进本身就是任务，完成一个演化周期即可调度下一周期；在经验驱动核心演化中，常规工作和社交交互暴露的 bug、粗糙之处及低效上下文构造会引发已评审的结构变更。在 Terminal-Bench 2.1 上，Opus 5 运行取得 86.74% 的得分，为该基准报告的最佳结果。We present Ouroboros, a self-developing agent harness whose tools, prompts, context assembly, and core implementation improve through reviewed commits that become the runtime for later work. Core evolution proceeds in two modes. In recursive free evolution, improvement is itself a task, and completing one evolution cycle can schedule the next. In experience-driven core evolution, ordinary work and social interaction expose bugs, rough edges, and inefficient context construction that lead to reviewed structural changes. On Terminal-Bench 2.1, an Opus 5 run scores 86.74%, the best result reporte

本文提出 Agent Memory Distillation (AMD)，一个无需训练、通过分层记忆将结构化知识从大型教师智能体迁移到小型学生智能体的框架，一致优于现有基于记忆的基线方法。Agent Memory Distillation (AMD), a training-free framework that transfers structured knowledge from a large teacher agent to a small student agent through hierarchical memory, is proposed, which consistently outperforms existing memory-based baselines.

本文提出 Combodied Agents——一种以人为中心的范式，借助软件工具、传感器、可穿戴设备、机器人与人工服务作为行动通道而非终极目标，在时间维度上感知、建模、预测并支持个体的人体状态轨迹。Combodied Agents is introduced, a human-centered paradigm that perceives, models, predicts, and supports individual human-state trajectories over time, using software tools, sensors, wearables, robots, and human services as action channels rather than end goals.

结果表明，剪枝效果更取决于剪枝应用的位置，而非具体的评分规则：早期剪枝带来最大的端到端节省，后期剪枝主要用于细化最终的合成上下文。The results show that pruning effectiveness depends more on where pruning is applied than on the specific scoring rule: early pruning yields the largest end-to-end savings, while later pruning mainly refines the final synthesis context.

本文提出 InSight-doc，一种智能体视觉感知框架，将视觉分辨率视为一种自适应的推理时资源，从低分辨率起步，选择性地放大高分辨率区域以获取更细粒度的证据，且不依赖任何外部检索器。This work proposes InSight-doc, an agentic visual perception framework that treats visual resolution as an adaptive reasoning-time resource that starts from low resolution and selectively zooms into high-resolution regions for finer evidence, without relying on any external retriever.

尽管方法简单，Decision Transformer 在 Atari、OpenAI Gym 和 Key-to-Door 任务上达到或超过 SOTA 无模型离线 RL 基线的性能Despite its simplicity, Decision Transformer matches or exceeds the performance of state-of-the-art model-free offline RL baselines on Atari, OpenAI Gym, and Key-to-Door tasks.

本文提出连续性核 (Continuity Kernel, CK)，一种激活契约，将提交前候选评估与原子状态激活解耦，将连续性定义为已接受分支头的连续且经过授权的谱系。The Continuity Kernel (CK), an activation contract that decouples off-commit candidate evaluation from atomic state activation from atomic state activation is presented, defining continuity as an unbroken, authorized lineage of accepted branch heads.

结果表明，长周期软件开发可以围绕持久化项目而非持久化智能体来组织；本文提出 EvoX Genesis，使软件项目保持持久，同时允许局部智能体保持有限生命周期。Results show that long-horizon software development can be organized around a persistent project rather than a persistent agent, and EvoX Genesis is introduced, which instead makes the software project persistent while allowing local agents to remain finite-lived.

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.

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.

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.

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.