论文

本文介绍 CLBench-V，一个多模态上下文学习 benchmark，围绕三个维度组织任务——上下文 grounding、新信息应用与新知识学习——以解决定位上下文使用失效位置的难题。This work introduces CLBench-V, a benchmark for multimodal context learning that addresses the difficulty of localizing where context use breaks down by organizing tasks around three dimensions: context grounding, new information application, and new knowledge learning.

提出 CAST（Credit Assignment from Solver Teachers），将游戏求解器状态价值的变化转换为求解器优势，并将其作为 turn 级信号注入 RLVR，在 ALFWorld 和 WebShop 上取得最高的平均 zero-shot 性能。CAST (Credit Assignment from Solver Teachers), which converts value changes in a game solver's state value into solver advantages and injects them into RLVR as turn-level signals and achieves the highest average zero-shot performance on ALFWorld and WebShop.

本文提出 CoRT，一种用于 rubric 条件化 GRPO 的 token 级 credit 加权方法，通过反事实回放在原始 rubric 条件化 prompt 和匹配的免准则 prompt 下对同一样本响应重新打分，并表明策略内部反事实似然对比为响应内 credit 分配提供了有效的训练信号。CoRT is proposed, a token-level credit weighting method for rubric-conditioned GRPO that uses counterfactual replay to rescore the same sampled response under the original rubric-conditioned prompt and a matched criteria-free prompt, and suggests that policy-internal counterfactual likelihood contrasts provide an effective training signal for within-response credit allocation.

介绍 StealthBench，一个跨越六个 OPSEC 维度衡量自主攻击性安全 agent 操作隐蔽性的 benchmark，并以公共 benchmark 形式发布，以支持隐蔽感知 agent 的开发及自主攻击性安全部署中的自动化 OPSEC 监控。StealthBench, a benchmark that measures operational stealth in autonomous offensive-security agents across six operational security (OPSEC) dimensions, is introduced and released as a public benchmark to support both the development of stealth-aware agents and automated OPSEC monitoring for autonomous offensive-security deployments.

本文贡献包括：圣训学概念到多 agent 流水线的形式化映射、实现 claim 链和分级 narrator 注册表的关系模式、结合链等级与内容批评的决策矩阵，以及对真实物理教材中 20,000 条 claim 的评估。A formal mapping from hadith-science concepts to multi-agent pipelines, a relational schema implementing claim chains and a graded narrator registry, a decision matrix combining chain grade with content criticism, and an evaluation on 20,000 claims from real physics textbooks are contributed.

描述一个 memory store：agent 本地的 Neo4j 属性图，增强 HNSW 向量索引，并采用完整的双时态数据模型，支持时间点语义检索而无需物理覆盖历史。A memory store is described: an agent-local Neo4j property graph augmented with HNSW vector indexes and a full bitemporal data model that supports point-in-time semantic retrieval without physically overwriting history.

提出知识对齐的多跳检索器 KAMR，区分受 query 强约束的 anchor triplet 和弱对齐但在结构上与 anchor 相连的 connected triplet，持续提升多跳检索及下游问答性能。A knowledge-aligned multi-hop retriever, KAMR, which distinguishes anchor triplets that are strongly constrained by the query from connected triplets that are weakly aligned yet structurally linked to the anchors, which consistently improves multi-hop retrieval and downstream question answering performance.

提出一个系统性的、以架构为中心的 LLM 记忆分类法，沿三个正交轴刻画记忆：表示、更新动态与持久性，有效桥接不同的架构范式。A systematic, architecture-centric taxonomy of memory in LLMs is presented, characterizes memory along three orthogonal axes: representation, update dynamics, and persistence, effectively bridging disparate architectural paradigms.

提出 MindForge，一个自动化 pipeline，将开源命令行程序转换为无源码环境（仅暴露编译后的可执行参考文件和文档），在全部 7 个未见软件工程 benchmark（涵盖长链路仓库生成与翻译）上一致优于基座模型。MindForge is introduced, an automated pipeline that converts open-source command-line programs into source-free environments that expose only a compiled reference executable and its documentation that consistently improves over the base model across all seven unseen software engineering benchmarks, spanning long-horizon repository generation and translation.

提出 SpecFirst，一个两阶段框架，在代码合成前强制进行需求 elicitation，并证明显式需求工程阶段是从零构建程序的有效范式。This work presents SpecFirst, a two-stage framework that forces the specification elicitation before code synthesis, and demonstrates that an explicit requirements-engineering phase is an effective paradigm for from-scratch program construction.

Voice Memory，一个面向 agentic 语音识别的纯推理方案：流式推理时，冻结 corrector 读取单一 per-domain memory，逐 utterance 决定是否作用于假设或弃权并保留 1-best，跨 corrector 族可迁移，推理路径不增加任何参数。Voice Memory, a inference-only scheme for agentic speech recognition: at stream time, a frozen corrector reads a single per-domain memory and decides per utterance whether to act on the hypothesis or abstain and keep the 1-best, and transfers across corrector families and adds zero parameters to the inference path.

提出 pi-r2-flow，使 action-chunking flow 策略具备实时响应能力，同时保留大型 backbone、表达力强的多模态策略与多动作预测能力，并给出延迟自适应 flow 调度，将 in-flight 动作作为 inpainting 条件，每次调用仅需一步去噪即可输出动作。This work presentspi-r2-flow, which makes action-chunking flow policies reactive and real-time while retaining large backbones, expressive multi-modal policies, and multi-action prediction, and a latency-adaptive flow schedule that treats in-flight actions as inpainting conditioning and emits actions in one denoising step per call.

提出 CADENCE，一个统一框架，对每种叠加式失败模式给出针对性修复，证明通过原则化的蒸馏即可在不依赖数据中心级硬件的条件下获得强推理质量。CADENCE, a unified framework with a targeted fix for each compounding failure modes, is presented, showing principled distillation reaches strong reasoning quality without datacenter-scale hardware.

提出 DualG-MRAG，一种面向多模态 RAG 的双层框架，解耦 Macro-reasoning 与 Micro-matching Graph 两类图结构，通过分离全局结构推理与细粒度证据匹配来抑制检索噪声，并引入动态规划解码机制，从 GNN 前向过程中直接提取显式推理路径。DualG-MRAG is proposed, a Dual-tier framework that introduces a decoupled architecture comprising Macro-reasoning and Micro-matching Graphs for Multimodal RAG to suppress retrieval noise by isolating global structural reasoning from fine-grained evidence matching, and introduces a dynamic programming decoding mechanism that extracts explicit reasoning paths directly from the GNN's forward pass.

引入一个基于 GLM 的 retriever，并在单跳与多跳 RAG 场景下对比分析 GLM-based、GNN-based 与传统向量检索 retriever 的相对优势，指出微调后的 GLM retriever 具有更好的跨域泛化能力。This work introduces a GLM-based retriever and investigates the comparative strengths of GLM-based, GNN-based, and traditional vector-search-based retrievers in single- and multi-hop RAG settings, and suggests that finetuned GLM retrievers generalize better out of domain.

提出 ConMem，一个面向 LLM 辅助设备巡检的贡献感知 memory 框架，支持人在环的早期风险筛查，并在受限 memory 预算下保留高价值证据。This work proposes ConMem, a contribution-aware memory framework for LLM-assisted equipment inspection, supporting a human-in-the-loop early-risk screening system and retaining high-value evidence under a constrained memory budget.

OptGraph 是首个引入 GraphRAG 的优化 agentic workflow，首次将可复用经验构建为类型化 graph，刻画建模模式、问题形式化、实现细节与错误修正之间的关系。OptGraph is the first optimization agentic workflow that introduces graph retrieval-augmented generation (GraphRAG) and first constructs reusable experience as a typed graph, capturing the relationships among modeling patterns, problem formalization, implementation details, and error corrections.

结果表明，长上下文 memory 可沿 layer 轴（而非仅沿 token 轴）进行组织，并揭示了有界检索的优势及其在窗口内的压缩代价。These results show that long-context memory can be organized along the layer axis, not only the token axis, and expose both the benefits of bounded retrieval and its in-window compression tax.

提出 PALATE（Person-Aligned LLM-Simulated-User Assessment with Tailored Evaluation），一个基于用户模拟器的可扩展 RPA benchmark，可针对具体 user-RPA 对给出可解释的评估，避免将系统压缩为单一、与用户无关的排名。PALATE (Person-Aligned LLM-Simulated-User Assessment with Tailored Evaluation with Tailored Evaluation), a scalable RPA benchmark built on user simulators, produces interpretable evaluations of specific user-RPA pairs rather than compressing systems into a single user-independent ranking.

提出 LedgerMind，配套三层 Grounding Protocol、一个按问题复杂度匹配推理深度的 Adaptive Dual-Path Dispatcher，以及一个具备形式化 provenance 非放大保证的事件触发验证与修复引擎，同时提升答案准确率与轨迹级忠实度。LedgerMind is introduced, augmented by a Three-Layer Grounding Protocol, an Adaptive Dual-Path Dispatcher that matches reasoning depth to question complexity, and an Event-Triggered Verification-and-Repair engine with a formal provenance non-amplification guarantee that improves both answer accuracy and trajectory-level faithfulness.

对有损验证方法所诱导的分布进行原则化分析，揭示一项根本缺陷：由于分布失真，其性能可能相对于真实截断采样基线显著退化。This work presents a principled analysis of the distributions induced by lossy verification methods, and identifies a fundamental pitfall: performance can degrade significantly compared to the true truncation sampling baseline due to distributional distortion.

ShadowDancer 引入 shadow pair，即在同一动力学下对外观做独立重采样的成对视频，并由 Shadow Library 大规模构建；一个 dynamics family 可控，当且仅当能为其构造出这样的 pair。ShadowDancer introduces shadow pairs, video pairs that replay the same dynamics under independently resampled appearance, constructed at scale by the Shadow Library, so that a dynamics family becomes controllable exactly when such pairs can be constructed for it.

记忆是长时程 LLM 智能体的核心，但现有记忆系统主要保存交互内容，而未建模哪些智能体在何种条件下可信。这一局限在多智能体系统中尤为关键，因为中心模型可能无法直接验证来自对等方、看似合理或相关的响应。我们提出 Σ-Mem，一种在线可靠性记忆，记录单个对等方的历史能力证据以及跨对等集的对等关系证据。两种证据均以实对称状态形式维护，并基于后Memory is central to long-horizon LLM agents, yet existing memory systems primarily preserve interaction content rather than modeling which agents can be trusted and under what conditions. This limitation is particularly important in multi-agent systems, where a central model may be unable to directly verify plausible or correlated peer responses. We introduce Σ-Mem, an online reliability memory that records historical competence evidence for individual peers and peer relationship evidence across the peer set. Both forms of evidence are maintained as real symmetric states and updated from post

对 Fairness Pruning 的实证评估表明，群体偏置处理与模型能力运行在可分离的电路上，奠定了从盲目零化向定向行为调制过渡的方法论基础。Empirical evaluation of Fairness Pruning empirically confirm that demographic bias processing and model capabilities operate on dissociable circuits, establishing the methodological foundations for transitioning from blind zeroing toward directional behavior modulation.

对代表性闭源与开源多模态模型的评测表明，视觉推理强依赖于模型与环境，没有任何单一设置能在所有任务上持续占优。Evaluating representative proprietary and open-source multimodal models, it is found that visual reasoning is strongly model- and environment-dependent, with no single setting consistently dominating across tasks.

将文件系统的默认设置转化为 agent memory 的设计空间，证明模型并非塑造 store 形态的唯一杠杆：仅调整工具集即可以与更换模型相当的力度重塑 store。The study turns the filesystem default from an assumption into a design space for agent memory, and turns the model is not the only lever over a store's shape: changing the tool set alone reshapes the store as strongly as swapping the model.

提出 MisKnow-Agent，一个受控评测框架，通过可控的权威线索与来源风格构造支撑人工审核结论的任务文档，并采用报告级 false-conclusion 采纳率（仅统计认可错误结论的报告），基于三种 backbone LLM 评估 DeerFlow 与 WebThinker。MisKnow-Agent is introduced, a controlled evaluation framework that constructs task-specific documents supporting manually audited false conclusions with controlled authority cues and source styles that evaluates DeerFlow and WebThinker with three backbone LLMs using a report-level false-conclusion adoption rate that counts only reports endorsing the false conclusion.

提出 OmniScope，一个无需训练的 token 压缩框架，以 query 作为跨模态共享的语义锚点，并对音频与视频分别估计相关性；由此给出 OmniLLM 推理的简单设计原则：跨模态共享 query，但不共享显著性估计。This work proposes OmniScope, a training-free token compression framework that uses the query as a shared semantic anchor while estimating relevance separately for audio and video, and suggests a simple design principle for OmniLLM inference: share the query across modalities, but not the salience estimates.

本 tutorial 综述近年来面向对话式 AI 的神经方法，并综述 SOTA 神经方法，揭示神经方法与传统符号方法之间的联系。This tutorial surveys neural approaches to conversational AI that were developed in the last few years, and presents a review of state-of-the-art neural approaches, drawing the connection between neural approaches and traditional symbolic approaches.

研究表明，领域特定的 orchestration 可使缺乏专业团队的实验室也能实现可审计的预处理，并为其他科学领域的 AI agent 提供了可借鉴的设计原则。The results indicate that domain-specific orchestration can bring auditable preprocessing within reach of laboratories lacking dedicated expertise, illustrating design principles applicable to AI agents in other scientific domains.

本工作识别出记忆溯源洗白现象：基于LLM的记忆整合过程中，外部观察可能被改写为看似用户历史或工作流支持的内容，在保留动作触发的同时，抹去本应限制其权威性的低可信度来源。This work identifies memory provenance laundering: during LLM-based memory consolidation, an external observation may be rewritten as apparent user history or workflow support, preserving an action trigger while erasing the low-trust source that should limit its authority.

教育agentic工程师需要系统性变革而非增量式课程改革：教学必须从产出工件转向对日益自主的社会-技术系统进行判断。It is concluded that educating the agentic engineer requires systemic transformation rather than incremental curricular change: instruction must shift from producing artifacts to exercising judgment over increasingly autonomous socio-technical systems.

提出统一框架，融合时频图结构学习与协变量感知的表示融合，证实其在建模选择性变量交互、利用协变量提升预测精度方面的有效性。This work proposes a unified framework integrating time–frequency graph structure learning with covariate-aware representation fusion, confirming its effectiveness in modeling selective variable interactions and leveraging covariates for improved forecasting accuracy.

提出Hypothetical Prompt Embeddings (HyPE)，将假设内容的生成从查询阶段前移到索引阶段，把检索转化为问题-问题匹配任务，无需运行时合成答案生成。This work proposes Hypothetical Prompt Embeddings (HyPE), a framework that shifts the generation of hypothetical content from query time to the indexing phase, and transforms retrieval into a question-question matching task, bypassing the need for runtime synthetic answer generation.

研究发现收敛后的扩散损失与提示中结构化语言量成比例关系，并采用两个互补度量：白盒似然指标(GPG)与黑盒属性指标(ED)。Surprisingly, it is found that the converged diffusion loss scales with the amount of structured language in the prompt, and two complementary measures are adapted: a white-box likelihood metric (GPG) and a black-box attribute metric (ED).

LlamaExtract Agentic Plus在三项指标上均排名第一，准确度可与coding agent相媲美而成本仅为其一小部分，是首个同时在大规模下对数值准确性、记录完整性、grounding与实测成本进行打分的方法。LlamaExtract Agentic Plus ranks first on all three metrics, with accuracy comparable to coding agents at a fraction of the cost, and is the first to score value accuracy, record completeness at scale, grounding, and measured cost together.