论文

结果表明，思维轨迹是推理任务的有效检索语料；将其转换为结构化、紧凑化或诊断式表征后，可释放出更强的增益。The results suggest that thinking traces are an effective retrieval corpus for reasoning tasks, and transforming them into structured, compact, or diagnostic representations unlocks even stronger gains.

本文提出 SCAR（Semantic Continuity-Aware Retrieval），一种自适应检索策略，通过权衡查询-邻居相关性与结构连续性惩罚来选择性扩展相邻分块，由此得到近似尺度不变的决策规则，无需重新校准即可跨 embedding 模型迁移。SCAR (Semantic Continuity-Aware Retrieval), an adaptive retrieval policy that selectively expands neighboring chunks by weighing query-neighbor relevance against a structural continuity penalty, is proposed, yielding an approximately scale-invariant decision rule that transfers across embedding models without recalibration.

本文提出 V-RAGBench——一个由 ⟨query, evidence chunk, answer⟩ 三元组构成的基准，可对检索与生成进行忠实且解耦的评估；同时提出 CARVE，一种在多种配置下并行运行检索器、并通过分块自适应重排序为每个分块挑选最优配置的简易方法。V-RAGBench is introduced, a benchmark of $\langle$ query, evidence chunk, answer$\rangle$ triplets that enables faithful, decoupled evaluation of retrieval and generation, and CARVE, a simple method that runs parallel retrievers across configurations and employs chunk-adaptive reranking to identify the winning configuration for each chunk.

本文提出 PathRouter，一种面向 agentic GraphRAG 的路径感知训练框架，沿答案正确性与证据路径重叠度联合评估每条轨迹，归纳出四类轨迹并采用差异化 GRPO 优势缩放，抑制捷径式强化同时保留证据寻求行为。This work presents PathRouter, a path-aware training framework for agentic GraphRAG that jointly evaluates each trajectory along answer correctness and evidence-path overlap, yielding four trajectory categories with differentiated GRPO advantage scaling that suppresses shortcut reinforcement while preserving evidence-seeking behavior.

本文提出 Diverge，一种即插即用的 agentic RAG 框架，通过迭代式、反思引导的多视角探索以及多样性感知检索支持来改善多样性—质量权衡，并引入用于刻画开放域问答中多样性—质量权衡的评估指标。Diverge is proposed, a plug-and-play agentic RAG framework that improves the diversity--quality trade-off through iterative, reflection-guided exploration of diverse viewpoints and diversity-aware retrieval support, and introduces evaluation metrics for characterizing the diversity-quality trade-off in open-ended question answering.

本文提出名为 InSemRAG 的 RAG 框架，通过迭代检索—校验机制及两个支撑模块——意图感知检索器（IAR）与语义保持切分（SPC）——应对上述挑战。This work proposes a RAG framework, termed InSemRAG, that addresses these challenges via an iterative retrieve-and-check mechanism with two supporting modules, an intention-aware retriever (IAR) and semantics-preserving chunking (SPC).

MRAgent，一种将联想记忆图与主动重构机制相结合的框架，将 LLM 推理直接融入记忆访问，确保记忆检索能动态适配推理上下文，同时避免无约束扩展引发的组合爆炸。MRAgent, a framework that combines an associative memory graph with an active reconstruction mechanism that integrates LLM reasoning directly into memory access, ensuring that memory retrieval is dynamically adapted to the reasoning context while avoiding combinatorial explosion caused by unconstrained expansion.

提出一个面向 RAG 的 AI 系统基准测试（RAGPerf）框架，用于刻画 RAG pipeline 的系统行为，并证明其引入的性能开销可忽略不计。The design and implementation of a RAG-based AI system benchmarking (RAGPerf) framework for characterizing the system behaviors of RAG pipelines is presented and it is shown that RAGPerf incurs negligible performance overhead.

本文首次系统分析了 LLM 如何通过强化学习（RL）学习针对不同 retriever 调整 query 表述策略，并揭示 RL 能有效教会 LLM 根据特定 retriever 特性定制 query。This work presents the first systematic analysis of how LLMs can learn to adapt their query formulation strategies for different retrievers via reinforcement learning (RL), and reveals that RL effectively teaches an LLM to tailor its queries to specific retriever characteristics.

本文旨在应对常见挑战并简化 RAG 与既有企业基础设施的集成，提出一套面向可扩展本地化部署企业 RAG 方案的综合性 AI 工程蓝图。This paper aims to address the gap in comprehensive on-premises RAG implementation frameworks by presenting a comprehensive AI engineering blueprint for scalable on-premises enterprise RAG solutions to address common challenges and streamline the integration of RAG into existing enterprise infrastructure.

本文提出 Retrieval-Augmented Speculative Decoding (RAPID)，利用 RAG 在长上下文推理中同时加速并提升生成质量，并设计了一种推理时知识迁移机制，通过 RAG 丰富目标分布。Retrieval-Augmented Speculative Decoding (RAPID) is introduced, which leverages RAG for both accelerating and enhancing generation quality in long-context inference and develops an inference-time knowledge transfer that enriches the target distribution by RAG.

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.

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.

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.

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.

提出一种审计方法，度量每个检索文档的留一因果影响，并对影响集中于低可信度文档的答案进行标记；并提出一种审计方法，度量每个检索文档的留一因果影响，并对影响集中于低可信度文档的答案进行标记。An audit is proposed that measures the leave-one-out causal influence of each retrieved document and flags answers whose influence concentrates on low-trust documents, and proposes an audit that measures the leave-one-out causal influence of each retrieved document and flags answers whose influence concentrates on low-trust documents.

本文提出 MathForm，一个通过 Mathlib 知识检索与验证引导的迭代优化来构建已验证训练数据的自动形式化框架，性能优于多个专用的 32B 自动形式化模型。MathForm is introduced, an autoformalization framework for constructing verified training data through Mathlib knowledge retrieval and verification-guided iterative refinement, and outperforming multiple specialized 32B autoformalizers.

本文提出 personalized auto-research 问题，将研究流程的每个阶段都以个体研究者的表征为条件，并提出了一个通用且灵活的框架，将基于图的研究者上下文贯穿于检索、假设搜索、实验、写作与评审之中。This work introduces the problem of personalized auto-research, which conditions every stage of the research process on a representation of the individual researcher, and proposes a general and flexible framework that threads a graph-grounded researcher context through retrieval, hypothesis search, experimentation, writing, and review.

读者特定的效用确实存在，但偏好并非干预：稳定的排序相似性不能授权帮助/伤害决策的迁移，稳定的序数相似性也无法预测跨读者的干预迁移。Reader-specific utility exists, but preference is not intervention: stable ranking similarity does not license transfer of help/harm decisions, and stable ordinal similarity fails to predict cross-reader intervention transfer.

提出 CoAL-RAG，一种复杂度感知的法律检索增强生成方法，通过构建基于"问题本质"与"检索一致性"的多维评估机制，实现检索策略的自适应路由。CoAL-RAG is proposed, a complexity-aware legal retrieval-augmented generation method, which constructs a multi-dimensional evaluation mechanism based on ``question essence'' and ``retrieval consistency'' to enable adaptive routing of retrieval strategies.

结果表明，Engram 可充当可复用的外部知识工件，前提是目标侧具备兼容的 Reader 接口；当直接复用 Reader 效果不足时，目标侧适配可进一步改善对齐效果。The results suggest that Engram can serve as a reusable external knowledge artifact, provided that the target has access to a compatible reader interface and target-side adaptation can further improve alignment when direct reader reuse is insufficient.

受搜索与推荐系统启发，本文构建了 Find、Attempt 与 Recommend（FAR），即一个从文献到综述的级联流程，可自动搜索合适的问题，并将人类注意力聚焦于经过多阶段筛选的成果上。Inspired by search and recommender systems, this work builds Find, Attempt, and Recommend (FAR), a literature-to-review cascade that automates the search for suitable problems and focuses human attention on artifacts that have passed several stages of filtering.

MissDiag 将聚合鲁棒性度量转化为类型化的诊断归因，为在不完备知识下比较、诊断和压力测试 KGQA 与 KG-RAG 系统提供了更具可解释性的基础。By transforming aggregate robustness measurement into typed diagnostic attribution, MissDiag provides a more interpretable basis for comparing, diagnosing, and stress-testing KGQA and KG-RAG systems under incomplete knowledge.

本文提出 IAR（Inject, Align, and Recover），一个三阶段后训练框架，将结构化文档知识注入、问答行为对齐与通用能力恢复解耦，提升面向无检索文档内化的"领域主—领域通"前沿。This work proposes IAR (Inject, Align, and Recover), a three-stage post-training framework that separates structured document knowledge injection, QA behavior alignment, and general ability recovery and improves the domain-primary domain-general frontier for retrieval-free document internalization.

本文提出 NAPE（Next-Audio-Patch-Embedding prediction），一个自监督框架：因果 Transformer 仅依据因果掩码与 stop-gradient，从先前 patch 嵌入预测对数梅尔频谱图的下一 patch 嵌入。NAPE (Next-Audio-Patch-Embedding prediction), a self-supervised framework in which a causal Transformer predicts each next patch embedding of a log-mel spectrogram from the previous ones, using causal masking and stop-gradient as its sole training signal is introduced.

本文为阿拉伯法学（fiqh）构建了一个检索测试集，并基于此评估稠密、词法、混合、微调及教法学派感知（madhhab-aware）等检索策略；错误分析表明，主要挑战在于区分包含答案的段落与主题相似但不含目标教法的段落。This work builds a retrieval test collection for Arabic fiqh and uses it to evaluate dense, lexical, hybrid, fine-tuned, and madhhab-aware retrieval strategies, and presents an error analysis showing that the main challenge is distinguishing answer-bearing passages from topically similar passages that do not contain the requested ruling.

这些结果支持一种分工：使用 embedding 模型处理相似度、分类与聚类任务，将 LLM 留给推理密集型的检索任务。These results support a division of labour: use embedding models for similarity, classification, and clustering, and reserve LLMs for reasoning-intensive retrieval, and reserve LLMs for reasoning-intensive retrieval.

本文提出 EnSI-RAG（Entity-Structure-Indexed Retrieval-Augmented Generation），通过构建查询无关、以实体为中心的索引，将证据定位与答案合成解耦，同时保留可追溯的源证据。This work proposes EnSI-RAG (Entity-Structure-Indexed Retrieval-Augmented Generation), a framework that constructs a query-independent, entity-centered index that separates evidence localization from answer synthesis while preserving traceable source evidence.

基于语音的应用在接入检索模块之前需先通过自动语音识别（ASR）处理口头查询，因此 ASR 错误会以固定的上游约束进入 pipeline。我们通过实验验证标准检索增强生成（RAG）的两项扩展——实体图链接与迭代式 query 改写——是吸收还是放大了这些错误。基于神经 TTS 合成的四种英语口音，我们在三个多跳 QA 基准（HotpotQA、2WikiMultiHopQA 和 MuSiQue）上评测四种 RAG 配置，以干净文本 oracle 为对照。尽管结构上更丰富的 configuratioSpeech-based applications pass spoken queries through automatic speech recognition (ASR) before any retrieval module, so ASR errors enter the pipeline as a fixed upstream constraint. We empirically test whether two extensions to standard retrieval-augmented generation (RAG), entity-graph linking and iterative reformulation, absorb or amplify these errors. Using four English accents synthesized through neural TTS, we evaluate four RAG configurations on three multi-hop QA benchmarks (HotpotQA, 2WikiMultiHopQA and MuSiQue) against a clean-text oracle. Although the structurally richer configuratio

本文提出 FORGE（Fake Online Recommendations in Generative Environments），将一组固定检索网页中的真实商品在本地改写为虚假商品，并在 15 个类别、5 种消费场景下的 225 件真实商品上，衡量 LLM 推荐虚假商品的频率。This work introduces FORGE (Fake Online Recommendations in Generative Environments), which locally rewrites real products in a frozen set of retrieved web pages into fake ones and measures how often the LLM recommends the fake product, across 225 real products in 15 categories and 5 consumer scenarios.

本文介绍 TianoForge，这是面向 TianoCore 开源 UEFI 固件开发生态中 bug 分诊的集成方案，部署 AI（具体为机器学习）领域的 SOTA 方法以实现自动化 bug 分诊。This integrated approach to bug triage in the TianoCore open-source UEFI firmware development ecosystem, called TianoForge, deploys the state of the art in artificial intelligence, specifically machine learning, to enable automated bug triage.

本文通过全面超越传统开环基线，证明了当前主流的单体上下文扩展策略是一种因相关性衰减而受到惩罚的架构陷阱，并确立了以顺序、反馈驱动的编排作为生成式搜索的确定性范式。By dominating classical open-loop baselines, this work proves that the prevailing strategy of monolithic context widening is an architectural trap penalized by relevance decay and establishes sequential, feedback-driven orchestration as the definitive paradigm for generative search.

提出 TRUSTMARGIN，一种免训练、即插即用的仲裁层，利用模型自身的似然对两个候选进行打分，在不微调、无需外部评判或额外生成的情况下，在直接回答与 RAG 之间进行选择。TRUSTMARGIN is proposed, a training-free, plug-and-play arbitration layer that scores the two existing candidates with the model's own likelihoods and selects between Direct and RAG without fine-tuning, external judges, or additional generation.

介绍 WeMM-Embedding，一族通用多模态嵌入模型，支持文本、图像、视频、视觉文档及任意交错的多模态输入，输出维度灵活，在多个公开基准上取得 SOTA 表现。WeMM-Embedding is presented, a family of universal multimodal embedding models supporting text, images, videos, visual documents, and arbitrarily interleaved multimodal inputs with flexible output dimensions and achieves leading performance on multiple public benchmarks.