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 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.

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.

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.

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.

本工作将 embedding 缩放作为正交于稀疏度缩放的强有力维度加以探索，并推出 LongCat-Flash-Lite，一个从零训练的 68.5B 参数、约 30 亿激活参数的模型，不仅超越参数等量级的 MoE 基线，还对同规模现有模型展现出卓越竞争力。This work explores embedding scaling as a potent, orthogonal dimension for scaling sparsity and introduces LongCat-Flash-Lite, a 68.5B parameter model with ~3B activated trained from scratch that not only surpasses parameter-equivalent MoE baselines but also exhibits exceptional competitiveness against existing models of comparable scale.

SarseX 模型无关、无需训练，并与 Prefix Cache 兼容，可为多轮对话、检索增强生成 (RAG) 和 Agent 工作流等常见在线服务场景提供统一支持。SarseX is model-agnostic, training-free, and compatible with Prefix Cache, and it provides unified support for common online serving scenarios including multi-round chat, retrieval-augmented generation (RAG), and agent workflows.

本文提出一个 Agentic RAG 框架，使 LLM 能够使用逻辑表达式构建检索意图，同时将检索后端简化为基于倒排索引的系统，并表明将检索过程锚定在逻辑查询上可显著降低生成响应中的幻觉。This paper proposes an agentic RAG framework that enables LLMs to formulate retrieval intents using logical expressions while simplifying the retrieval backend to an inverted-index-based system, and shows that anchoring the retrieval process in logical queries substantially reduces hallucinations in generated responses.

提出 MMAgent-R$^2$，一种将视觉重排序与主动拒答作为内部验证机制的 Agentic mRAG 框架，并通过 GRPO 训练实现外部检索、内部验证与答案生成的联合优化。MMAgent-R$^2$, an agentic mRAG framework that integrates visual reranking and active rejection as its internal verification mechanism, is proposed and achieves joint optimization of external retrieval, internal verification, and answer generation via GRPO training.

提出一种基于不确定性感知框架的自适应问答方法，通过 LLM 内部表征中区分知识不足与知识歧义/冲突的显式信号，在单次前向传播中即可由隐状态高效估计。This work proposes an uncertainty-aware framework for adaptive QA based on explicit signals derived from LLM internal representations that distinguish between knowledge insufficiency and knowledge ambiguity or conflict, and efficiently estimate these from hidden states in a single forward pass.

提出 DynaKRAG，将多跳证据获取建模为针对原子证据操作的状态条件控制，并展示了在演化证据状态下协同检索、诊断与缺口定向获取的优势。DynaKRAG is introduced, which formulates multi-hop evidence acquisition as state-conditioned control over atomic evidence operations, and demonstrates the benefit of coordinating retrieval, diagnosis, and gap-directed acquisition under an evolving evidence state.

提出一种新颖的进化系统，专注于利用 RAG 增强的 LLM 自动生成空域隐写的代码级代价函数；该方法在隐写安全性上一致优于现有自动设计方法，同时提高了平均代码执行率并降低了搜索成本。A novel evolutionary system focused on exploiting Retrieval-Augmented Generation enhanced LLMs for the automatic code-level generation of spatial steganography cost functions, which consistently achieves higher steganographic security than existing automatically designed methods and increases the average code execution rate while reducing the search cost.

该工作提出了一个端到端的档案处理与检索框架，将大语言模型（LLM）集成到档案流程中，并证明将 LLM 与成熟的文档处理与检索流程相结合，可将数字图书馆从静态存储库提升为可交互、可语义检索的档案系统。This work presents an end-to-end archival processing and retrieval framework that integrates large language models (LLMs) into the archival pipeline and demonstrates that integrating LLMs with established document processing and retrieval pipelines can elevate digital libraries from static repositories to interactive, semantically searchable archival systems.

本文提出 SOLAR，一种学习增强框架，从 regret 累积中推导修改时机，并基于隐式检索反馈的贝叶斯在线学习进行内容选择，实现与缓存大小和时域无关的常数竞争比。SOLAR is proposed, a learning-augmented framework that derives modification timing from regret accumulation and content selection from Bayesian online learning over implicit retrieval feedback and achieves a constant competitive ratio, independent of cache size and horizon.

提出 MEDIAREF：源自网络文档的公共知识库，支持跨 200 个媒体来源、可复现且低成本的 MBC 生成评估；给出可复现的构建与更新方法，并系统评测主流 LLM 在 MBC 生成任务上的表现。MEDIAREF, a publicly available knowledge store of web-sourced documents that enables reproducible, low-cost evaluation of MBC generation across 200 media sources, is introduced, describing a reproducible methodology for constructing and updating the collection, and assessing widely used LLMs on the MBC generation task.

CheckRLM：通过 RAG 及时校验并修正事实错误的框架，有效提升推理过程的可靠性，大幅超越现有基线。CheckRLM is a framework that improves the reliability of the reasoning process through Retrieval-Augmented Generation (RAG) by timely checking and correcting factual errors, and substantially outperforms existing baselines.

本文提出基于检索增强生成的多模态大学聊天机器人，将 LLM 与语义检索相结合，从以学校为中心的资源（如大学手册）中生成基于上下文的回复。This work presents the multimodal university chatbot with retrieval-augmented generation, which combines the large language model with semantic retrieval to produce context-based responses from institution-centric resources, such as the university handbook.

提出 Logit 贡献度评分（LOCOS），一种可感知写入的检测器，通过将每个注意力头的 OV 电路输出投影到答案 token 的去嵌入方向进行打分，在单次前向传播中对比 needle 与非 needle 源位置。Logit-Contribution Scoring (LOCOS) is introduced, a write-aware detector that scores each head by the projection of its OV-circuit output onto the answer-token unembedding direction, contrasting needle and off-needle source positions in a single forward pass.

仅启用记忆（不修改模型的任务-动作行为）即可将基础 Agent 性能提升约 2–4 倍，使 32B 开源权重模型具备与 Claude Opus 4.5、Gemini 3.1 Pro Thinking 等前沿系统相竞争的能力。Opting memory alone--without modifying the model's task-action behavior--improved the base agent's performance ~2x-4x, bringing a 32B open-weight model competitive with frontier systems such as Claude Opus 4.5 and Gemini 3.1 Pro Thinking.

结果表明，在重建频繁或高维场景中（如 multiprobe grid 等）基于网格的方法可能具有竞争力，因为这些场景下索引成本与维度鲁棒性决定性能。The results suggest that grid-based methods such as multiprobe grid may be competitive in rebuild-heavy or high-dimensional settings where indexing cost and dimensional robustness dictate performance.

AdaTrans 是一个通过三大核心机制解决 C 代码到 Rust 自动转换的框架：策略驱动的检索增强生成（RAG）机制，用于将编译器错误映射到具体修复；错误分层转换策略（ESTS），可根据错误类型自适应调整行为；以及多阶段验证流水线，以确保可编译性与功能等价性。AdaTrans is a framework that addresses the automated transformation of C code to Rust through three core mechanisms: a Strategy-Driven Retrieval-Augmented Generation (RAG) mechanism to map compiler errors to specific repairs, an Error-Stratified Transformation Strategy (ESTS) that adapts its behavior based on error types, and a multi-stage validation pipeline to ensure both compilability and functional equivalence.

AGE 专注于预测关键节点以外的节点，采用可学习节点采样器，在基于非参数检索组件的 GraphQA 任务上取得显著提升，在四个具有不同特征的基准数据集上均达到更高的准确率。AGE focuses on predicting nodes apart from key nodes, utilizing a learnable node sampler, and significantly improves approaches using non-parametric search component in GraphQA tasks, achieving superior accuracy across four benchmark datasets with distinct characteristics.

本文提出 SHIFT，一种新颖的框架，将神经元级修改重构为可学习的门控调制，使 LLM 能够自适应地调节内部激活以解决知识冲突。SHIFT is introduced, a novel framework that reformulates neuron-level modification as learnable gate modulation, allowing LLMs to adaptively regulate internal activations for knowledge conflict resolution, allowing LLMs to adaptively regulate internal activations for knowledge conflict resolution.

提出 ZooClaw-FashionSigLIP2——一款面向时尚领域的专用 SigLIP2-base 模型，以简洁方案化解该权衡，性能上优于 LoRA、更大骨干网络以及外部训练数据。ZooClaw-FashionSigLIP2, a fashion-specialized SigLIP2-base model that resolves this tradeoff with a simple recipe and outperforms LoRA, larger backbones, and external training data, is presented.

核心结论是"过时事实错误率"：在被要求作答时，RAG 有 15%–40% 的概率输出已被取代的旧值；MemStrata 将该比率降至约 0%，而这一类失效是 RAG 本身无法规避的。The central result is the stale-fact-error rate: when required to answer, RAG serves superseded values 15-40% of the time; MemStrata drives this to ~0%, a failure class RAG cannot avoid.

提出一种面向 LCA 解释的视角条件化检索增强生成框架，在 AI 辅助的 LCA 中引入多视角检索与受控合成，以支持超出传统 LCA 研究的、面向落地的决策。A perspective-conditioned retrieval-augmented generation framework for LCA interpretation, where a multi-perspective retrieval and controlled synthesis is incorporated in the artificial intelligence (AI)-assisted LCA to support implementation-oriented decision-making beyond conventional LCA studies.

本文提出 TRACE——一种通过 token 影响归因追踪答案相关 token 来识别投毒攻击的轻量检测框架；该方法首先发现跨检索文档的反复出现的高影响关键词，再经二次验证确认其对模型预测的影响。TRACE is presented, a lightweight detection framework that identifies poisoning attacks by tracing answer-related tokens through token influence attribution, and first discovers recurrent high-influence keywords across retrieved documents and then performs a secondary verification to confirm their influence on model predictions.

本文全面审视集中式、设备端、联邦与混合范式下 RAG 系统的隐私与安全挑战，并勾勒出构建可信、安全、韧性 RAG 系统的开放性研究挑战。A comprehensive examination of privacy and security challenges across RAG systems deployed in centralized, on-device, federated, and hybrid paradigms is provided and open research challenges toward building trustworthy, secure, and resilient RAG systems are outlined.