论文

GLM 将推理分解为分类、推理、动作生成与图检索等专用 Agent，支持分支化与选择性上下文共享，在保持推理质量的同时降低 prompt 长度与推理迭代次数，从而提升准确率并减少整体 token 消耗。GLM decomposes reasoning into specialized agents for classification, reasoning, action generation, and graph retrieval, enabling branching and selective context sharing to reduce prompt length and reasoning iterations while preserving reasoning quality, thereby improving accuracy and reducing overall token consumption.

研究发现 RLMs 能够成功处理超出模型上下文窗口长达两个数量级的输入，即便在较短 prompt 下，其质量也显著优于原生前沿 LLM 以及常见的长上下文与编程脚手架。It is found that RLMs can successfully process inputs up to two orders of magnitude beyond model context windows and, even for shorter prompts, dramatically outperform the quality of vanilla frontier LLMs and common long-context and coding scaffolds.

本文提出一个多 Agent 框架，由主 LLM 协调 grounding agent 定位与问题相关的片段，并协调 vision agent 提取目标文本观测，显著优于强非 Agent 基线，且强化学习进一步增强了已训练 Agent 的推理与规划能力。A multi-agent framework in which a master LLM coordinates a grounding agent to localize question-relevant segments and a vision agent to extract targeted textual observations is proposed, which significantly outperforms strong non-agent baselines and shows reinforcement learning further strengthens reasoning and planning for the trained agent.

本文提出 ReMemR1，将 memory retrieval 机制融入 memory update 过程，使 Agent 能够选择性回溯历史记忆以进行非线性推理，并设计多级奖励机制，将最终答案奖励与密集的 step 级信号相结合，引导对 memory 的有效使用。This work presents ReMemR1, which integrates the mechanism of memory retrieval into the memory update process, enabling the agent to selectively callback historical memories for non-linear reasoning, and proposes a multi-level reward design, which combines final-answer rewards with dense, step-level signals that guide effective memory use.

本研究建立了一套实用的 LongPT 方案，为推进长上下文 vision-language 模型奠定了经验基础，并提出 MMProLong，无需任务专属监督即可泛化至基于网页的多模态 needle 检索、长上下文图文压缩以及长视频理解等任务。This study establishes a practical LongPT recipe and an empirical foundation for advancing long-context vision-language models, and introduces MMProLong, which generalizes to webpage-based multimodal needle retrieval, long-context vision-text compression, and long-video understanding without task-specific supervision.

本文提出 LLaDA-V，一种完全基于扩散范式的多模态大语言模型 (MLLM)，将视觉指令微调与 masked diffusion 模型相结合，脱离了当前多模态方法中主流的自回归范式。LLaDA-V is introduced, a purely diffusion-based Multimodal Large Language Model (MLLM) that integrates visual instruction tuning with masked diffusion models, representing a departure from the autoregressive paradigms dominant in current multimodal approaches.

总体而言，分阶段检索的影响往往超过"理想证据存在"本身；本文为专业科学场景下 RAG 系统的部署与诊断提供了实践指导，并为构建更可靠、可控的迭代式检索-推理框架奠定了基础。This is the first controlled, mechanism-level diagnostic evaluation of whether synchronized iterative retrieval and reasoning can surpass even an idealized static upper bound (Gold Context) RAG, and practical guidance for deploying and diagnosing RAG in specialized scientific settings.

Decentralized Language Models (DeLM) 是一种 MAS 框架，通过并行 Agent、共享已验证上下文与任务队列实现去中心化协作，在软件工程 test-time scaling 与长上下文推理两方面均取得提升。Decentralized Language Models (DeLM), a MAS framework that decentralizes coordination through parallel agents, a shared verified context, and a task queue, improves both software-engineering test-time scaling and long-context reasoning.

揭示使用工具的 LLM Agent 的一种部署失效模式——来源缺口，以及一类跨上下文多步越狱攻击，可在早期交互中保留看似无害的中间产物，并在很久以后（可能在不同 Agent 实例或工作流阶段）诱发有害行为。A deployment failure mode for tool-using LLM agents, the provenance gap, and a family of cross-context multi-step jailbreaks that preserve benign-looking intermediate artifacts from an early interaction and elicit harmful behavior much later, potentially in a different agent instance or workflow stage.

提出一种自我演化的法律 Agent 框架，将 Model、Harness、Agent 角色、法律 Knowledge、确定性 Tools 与程序性 Skills 拆分为可审计的层面，用于来源可追溯性、日期与数字的事实校验、交付物合规性以及问题闭环。A self-evolving legal-agent framework that factors Model, Harness, Agent roles, legal Knowledge, deterministic Tools, and procedural Skills into auditable surfaces for source traceability, date and number grounding, deliverable compliance, and issue closure is introduced.

引入 D（Domain-Collection-Document），一种面向领域的设计，用于在不修改底层语言模型的前提下组织 RAG 系统中的知识并控制查询处理。D (Domain-Collection-Document), a domain-oriented design to structure knowledge and control query processing in RAG systems without modifying the underlying language model, is introduced.

提出 Tail-Aware Adaptive-k（TAA-k），一个无需训练、通过局部验证策略将 EVT 落地的框架，检索质量接近 oracle，相较全局 EVT 方法获得数量级的效率提升，并在不同 embedding 模型和压缩维度下保持稳健。Tail-Aware Adaptive-k (TAA-k), a training-free framework that operationalizes EVT through a localized validation strategy, is proposed, which achieves near-oracle retrieval quality with orders-of-magnitude efficiency gains over global EVT methods, while maintaining robustness across embedding models and compression dimensions.

本文提出后确定性分布式系统（PDDS）作为一种研究与工程模型，用于协调确定性代码、随机模型与自主 Agent 共存的异构环境，并证明经典分布式计算模型是该参与者通用模型的零模糊特例。This paper introduces Post-Deterministic Distributed Systems (PDDS) as a research and engineering model for coordinating heterogeneous environments where deterministic code, stochastic models, and autonomous agents coexist, and shows that classical distributed computing models form a zero-ambiguity special case of this participant-general model.

在两台生产超级计算机上对三种 SOTA 向量数据库进行大规模评估，扩展至 64 个计算节点上的 256 个分布式 worker，结果显示：工作负载特性可能限制延迟下降，增加核心反而会降低查询吞吐，且从 16 扩展至 256 个 worker 仅带来 5.46 倍的性能提升。A large-scale evaluation of three state-of-the-art vector databases on two production supercomputers, scaling to 256 distributed workers across 64 compute nodes, reveals that workload characteristics can limit latency reduction, additional cores can reduce query throughput, and scaling from 16 to 256 workers only yields a 5.46x improvement.

通过形式化分析与架构分解，展示 SSGM 如何缓解拓扑引发的知识泄漏（敏感上下文被固化到长期存储），以及有助于防止语义漂移（知识在迭代摘要中退化）。Through formal analysis and architectural decomposition, it is shown how SSGM can mitigate topology-induced knowledge leakage where sensitive contexts are solidified into long-term storage, and help prevent semantic drift where knowledge degrades through iterative summarization.

提出 Stratum，一种统一系统基础设施，在 agentic pipeline 搜索期间将 pipeline 执行与规划和推理解耦，无缝集成现有 Python 库，将批量 pipeline 编译为优化的执行图，并通过基于 Rust 的新型 runtime 等异构后端高效执行。Stratum is proposed, a unified system infrastructure that decouples pipeline execution from planning and reasoning during agentic pipeline search, and integrates seamlessly with existing Python libraries, compiles batches of pipelines into optimized execution graphs, and efficiently executes them across heterogeneous backends, including a novel Rust-based runtime.

HERA 是一个分层框架，联合演化多 Agent 编排与角色特定的 Agent prompt，在多 Agent RAG 中实现针对性的、角色条件化的改进，并提供角色感知的 prompt 演化。HERA is a hierarchical framework that jointly evolves multi-agent orchestration and role-specific agent prompts, enabling targeted, role-conditioned improvements in multi-agent Retrieval-Augmented Generation and Role-Aware Prompt Evolution.

本文在 KV cache 约束下对 LLM 推理进行理论建模，提出一种新型批处理与调度算法，在有效管理 KV cache 内存的同时最小化推理延迟，并通过在合成数据集上与后视最优的对比展示其强劲的实证性能。This work model LLM inference with KV cache constraints theoretically and proposes a novel batching and scheduling algorithm that minimizes inference latency while effectively managing the KV cache's memory, and demonstrates the algorithm's strong empirical performance by comparing it to the hindsight optimal in a synthetic dataset.

本文构建一种针对 GitHub issue 的持久会话评估方法，锚定在单一 base commit，对线性顺序探索与非线性、领域范围的并行 agentic 探索进行比较。This work constructs an approach for persistent-session evaluation of GitHub issues anchored at a single base commit, and compares linear sequential exploration against non-linear, domain-scoped parallel agentic exploration.

本文系统梳理了 Agent 系统从 pre-LLM 时代到当前 LLM 驱动架构的演进，将其划分为软件型、物理型与自适应混合型，并突出展示了其在客户服务、软件开发、制造自动化、个性化教育、金融交易和医疗等领域的应用。This paper comprehensively examines the evolution of agent systems from the pre-LLM era to current LLM-powered architectures, categorizing agent systems into software-based, physical, and adaptive hybrid systems, highlighting applications across customer service, software development, manufacturing automation, personalized education, financial trading, and healthcare.

本文认为 UQ 研究必须转向面向交互式 Agent 的现实场景，需要一套面向 Agent 的新原则性框架，并首次提出了能涵盖现有 UQ 设置的 Agent UQ 通用形式化方法。This paper argues that UQ research must shift to realistic settings with interactive agents, and that a new principled framework for agent UQ is needed, and presents the first general formulation of agent UQ that subsumes broad classes of existing UQ setups.

结果表明，在所评估的协调者–工作者设定下，多 Agent 系统中的隐私风险主要由架构层面的协调通道决定，而非仅取决于最终输出行为：风险来源于对标准输出级防御不可见的内部通道。Results suggest, within the evaluated coordinator-worker setting, that privacy risk in multi-agent systems is strongly shaped by architectural coordination channels rather than final-output behavior alone: it arises from internal channels that remain invisible to standard output-level defenses.

文中指出，安全的 LLM Agent 需要显式的信任边界、原则化的权限控制、具备溯源能力的 state 管理，以及与真实运行场景对齐的评估实践；现有 benchmark 仍未能充分覆盖长程、具状态、对部署敏感的风险。It is argued that secure LLM agents require explicit trust boundaries, principled privilege control, provenance-aware state management, and evaluation practices aligned with realistic operational settings, as well as existing benchmarks still underrepresent long-horizon, stateful, and deployment-sensitive risks.

文中认为，编码 Agent 已跨越能力门槛，传统的人工 code review 已不再是软件质量流水线的必要环节。It is argued that coding agents have crossed a threshold of capability at which traditional human code review is no longer a necessary component of a software quality pipeline.

在 DeNovoSWE 上对 Qwen3-30B-A3B 进行微调可显著提升长程 SWE 性能，在具有挑战性的 BeyondSWE-Doc2Repo benchmark 上将其得分从 5.8% 提升至 47.2%。Fine-tuning Qwen3-30B-A3B on DeNovoSWE substantially improves long-horizon SWE performance, raising its score on the challenging BeyondSWE-Doc2Repo benchmark from 5.8% to 47.2%.

本综述系统梳理了超越基础 Skill 创建的 Skill 演化与评估图景，将其归纳为四种范式：执行反馈、轨迹蒸馏、压缩与强化学习，并指出了构建可泛化、高效且可验证安全的 Skill 生态的开放方向。This survey systematically examines the landscape of skill evolution and evaluation beyond foundational skill creation into four distinct paradigms, spanning execution feedback, trajectory distillation, compression, and reinforcement learning, and identifies open directions for building skill ecosystems that are generalizable, efficient, and verifiably safe.

该方法通过在现有企业搜索基础设施之上叠加一层轻量级 harness，为推理型 LLM 配备 search、find、open、summarize 等工具，使其能够自主地迭代检索信息、跨文档导航并分析证据，从而降低对单一环节的过度依赖。The approach reduces this overdependence by layering a lightweight harness on top of existing enterprise search infrastructure, equipping a reasoning LLM with search, find, open, and summarize tools enabling the model to iteratively retrieve information, navigate within documents, and analyze evidence autonomously.

本文提出了一种实证方法，用于研究基于 GPU 的 LLM 推理服务系统中的 software aging 问题，并提供了一个可复现的框架，开辟了 software aging 与 software rejuvenation 与 LLM serving 交叉方向的研究。This paper proposes an empirical methodology to study software aging in GPU-based LLM serving systems and provides a reproducible framework that opens a research direction at the intersection of the software aging and rejuvenation and LLM serving communities.

分析表明，鲁棒的长期记忆（Long-Term Memory）安全无法仅在 retrieval 或执行阶段后置加固，而必须在最初就以存储阶段的溯源、版本化与策略感知的 retention 为基础进行锚定。This analysis indicates that robust Long-Term Memory security cannot be retrofitted at retrieval or execution time alone, but must be anchored in storage-time provenance, versioning, and policy-aware retention from the outset.

本文推出 STEP3-VL-10B，一个面向"紧凑效率与前沿级多模态智能"权衡的轻量级开源基础模型，并发布完整模型套件，为社区提供强大、高效且可复现的 baseline。STEP3-VL-10B is presented, a lightweight open-source foundation model designed to redefine the trade-off between compact efficiency and frontier-level multimodal intelligence, and the full model suite is released to provide the community with a powerful, efficient, and reproducible baseline.

本文概述了第二届 MAGMaR（Multimodal Retrieval 驱动的多模态增强生成）研讨会共享任务的成果，参赛系统聚焦于视频检索，或在给定检索视频的基础上进行有依据的文章生成。This overview paper presents the results of the shared task for the second workshop on Multimodal Augmented Generation via Multimodal Retrieval (MAGMaR), where participants submitted systems focused on either video retrieval or grounded generation of articles given retrieved videos.

本文提出首个将计算与 GPU 显存约束显式纳入 LLM 推理分析的排队论框架，并推导了严格的稳定性与不稳定性条件，用以判定 LLM 推理服务能否在持续到达的请求下避免队列无界增长。This paper introduces the first queueing-theoretic framework that explicitly incorporates both computation and GPU memory constraints into the analysis of LLM inference, and derives rigorous stability and instability conditions that determine whether an LLM inference service can sustain incoming demand without unbounded queue growth.

文章认为基于实体的分解能形成对原始信息更精炼的表示，并有助于降低索引与生成过程中的噪声；在端到端 QA 评测中，VectorRAG 表现优于标准 GraphRAG，且接近当前 SOTA 图方法的效果。It is argued that entity-based decomposition yields a more distilled representation of original information, and additionally serves to reduce noise in the indexing, and generation process, and on end to end QA evaluation VectorRAG performs better than standard GraphRAG and almost as good as current SOTA graph-based solutions.

提出 SIFT：Selective-Index For Fast Compute of RAG Prefill by Exploiting Attention Invariance，离线处理文档并提取每个文档中高分注意力的细粒度位置，以两个紧凑的位向量存储这些高分位置。SIFT: Selective-Index For Fast Compute of RAG Prefill by Exploiting Attention Invariance is proposed, which processes documents offline and extracts fine-grained locations of high attention scores for each document and stores locations of high scores in the form of two compact bit vectors.

本综述界定了 CAIS 的概念，提出基于组件角色与编排策略的多维分类体系，并分析四种基础范式：Retrieval-Augmented Generation (RAG)、LLM Agents、Multimodal LLMs (MLLMs) 与 Orchestration。This survey defines the concept of CAIS, proposes a multi-dimensional taxonomy based on component roles and orchestration strategies, and analyzes four foundational paradigms: Retrieval-Augmented Generation (RAG), LLM Agents, Multimodal LLMs (MLLMs), and Orchestration.