论文

本文提出 SpectralShift，一种用于 GDN 长上下文持续预训练的谱重参数化方法，通过重参数化 alpha 投影的初始化以重塑衰减谱，增强慢传播能力，并进一步引入 alpha 投影的学习率缩放以促进长上下文训练。SpectralShift is proposed, a spectral reparameterization approach for long-context continual pretraining of GDNs that reparameterizes the alpha projections initialization to reshape the decay spectrum by enhancing slow propagation capacity, and further introduces a learning-rate scaling for alpha projections to facilitate long-context training.

本文提出 SELF-INDEX，一个无需人工干预即可让索引自我演进的框架；其 Optimizer 可自主诊断检索短板，选择性修改对应的索引键，并在每次更新前对每项修订进行验证。SELF-INDEX is proposed, a framework that enables an index to self-evolve without human intervention, and its Optimizer autonomously diagnoses retrieval shortfalls, selectively revises the responsible index keys, and validates each revision before updating the index.

Mixture of Memory Embeddings (MoME)：一种上下文感知的记忆机制，将每个 token 的单一记忆行替换为 M 个 slot 的混合，并通过隐藏状态上的可学习门控选择在每个位置读取哪些 slot；在 sub-billion 规模下展现出更优的记忆容量 scaling 趋势，且训练与推理均保持高效。Mixture of Memory Embeddings (MoME), a context-aware memory mechanism that replaces each token's single memory row with a mixture of M slots and uses a learned gate over the hidden state to choose which slots to read at each position, shows more promising memory-size scaling trend at sub-billion scale and remains efficient in training and inference.

本文将 Agentic 检索-生成循环形式化为有限时域部分可观测马尔可夫决策过程，显式建模其控制策略与状态转移，并构建了全面的分类体系与模块化架构分解，按规划机制、检索编排、记忆范式与工具调用行为对系统进行分类。This paper formalizes agentic retrieval-generation loops as finite-horizon partially observable Markov decision processes, explicitly modeling their control policies and state transitions, and develops a comprehensive taxonomy and modular architectural decomposition that categorizes systems by their planning mechanisms, retrieval orchestration, memory paradigms, and tool-invocation behaviors.

提出 Document Retrieval-Aware Chunking (D-RAC)，将 Web Retrieval-Aware Chunking (W-RAC) 框架扩展至任意文档格式，保留 W-RAC 的成本、确定性与可观测性优势，同时将每种可渲染格式解锁为一类输入。Document Retrieval-Aware Chunking (D-RAC), an extension of the Web Retrieval-Aware Chunking (W-RAC) framework to arbitrary document formats, is presented, preserving W-RAC's cost, determinism, and observability benefits while unlocking every renderable format as a first-class input.

提出 Functionalizer，一种无损预分词框架，将正字与结构变体分解为分词前的可组合操作码/操作数前缀流：以 Unicode 私有使用区编码的参数化变换操作符（操作码）为前缀，连接规范基础 token（操作数）。The Functionalizer is presented, a lossless pre-tokenizer framework that factors orthographic and structural variations into a compositional opcode/operand prefix stream before tokenization: a canonical base token (operand) prefixed by parametric transformation operators (opcodes) encoded in the Unicode Private Use Area.

一种近期且有效的方法：通过一个小型 low-rank adapter，将大型预训练图像编辑模型适配到图像恢复任务，并以源自退化图像本身的 instruction 替代 text prompt；在同等条件下该方法优于文本条件。A recent and effective recipe adapts a large pretrained image-editing model to restoration using a small low-rank adapter with a text prompt to an instruction derived from the degraded image itself that outperforms text conditioning under a matched comparison.

论文论证了物理先验提供了一种与机器人领域高度相关的归纳偏置，其作用是与数据驱动学习互补而非取代，从而为更通用、数据高效且可信的机器人系统铺平道路。It is argued that physics priors provide a particularly relevant robotics-specific inductive bias, complementing rather than replacing data-driven learning, and paving the way toward more generalizable, data-efficient, and trustworthy robotic systems.

结果支持将生成式记忆视为对直接检索的选择性修正，并强调何时、以何种方式、以何种强度进行路由干预是核心挑战。The results support generated memory as a selective correction to direct retrieval and highlight routing when, which, and how strongly to intervene as the central challenge.

本文提出 ZooWork-ShopRanker，一族对齐到裁判标注购物偏好的电商 reranker，以及 ShopRank-Bench，一个包含约 10,000 条私有流量偏好对的低污染 benchmark，按承诺该标注的裁判家族数量分档呈现，覆盖多种文本格式。ZooWork-ShopRanker, a family of e-commerce rerankers aligned to judge-labeled shopping preference, and ShopRank-Bench, a contamination-limited benchmark of ~10,000 private-traffic preference pairs in both text formats, tiered by how many judge families committed to each label.

QReason 是一种解耦框架，将面向 query 的推理与针对窗口的 passage 相关性评估分离，显著减少冗余推理，在取得与 reasoning-based reranker 相当乃至更优的排序性能的同时，超越了现有的 query rewriting 模型。QReason is a decoupled framework that separates query-focused reasoning from window-specific passage relevance assessment, and significantly reduces redundant reasoning, achieves ranking performance comparable to or better than strong reasoning-based rerankers, and outperforms existing query rewriting models.

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.

BoundaryMORPH 是一种新算法，专门为 LLM 的上下文容量 k 分配 CE 预算，在多个模型与数据集上针对开放性查询取得了 SOTA 集合检索质量。BoundaryMORPH is introduced, a novel algorithm that allocates CE budget specifically for the LLM's context capacity $k$ and achieves state-of-the-art set retrieval quality across multiple models and datasets with open-ended queries.

本文提出一个新颖的初步框架，可定量评估输出格式不同（如列表与消息）的检索系统的 IR 准确度，为客观评估基于关键词与基于语义的对话式检索方法奠定坚实基础。This work introduces a novel, preliminary framework to quantitatively assess IR accuracy of search systems that produce different output formats, such as lists and messages, and provides a strong foundation for objectively assessing keyword-based and semantic chat-based search methods.

RAGScope 是一个泄漏受控的评估协议，用于评估仅使用任务输入、检索上下文和答案文本的本地证据门，结合了上下文分组划分、折范围预处理、组自举区间、部署工作点、端到端运行时以及显式的源偏移压力测试。RAGScope, a leakage-controlled protocol for evaluating local evidence gates that use only the task input, retrieved context, and answer text is presented, which combines context-grouped splits, fold-scoped preprocessing, group bootstrap intervals, deployment operating points, end-to-end runtime, and explicit source-shift stress tests.

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.

本综述对 RAG 进行了全面考察，将其视为一个模块化且持续演进的范式，能够提升基于 LLM 系统的事实可靠性、适应性与任务对齐，并指出了持续存在的挑战。This survey presents a comprehensive examination of RAG as a modular and evolving paradigm that enhances factual reliability, adaptability, and task alignment in LLM based systems and identifies persistent challenges.

提出一种自适应、自动化的数据提取攻击流程，在黑盒设置下针对 MRAG（其中检索到的视觉产物本身就是答案）发起攻击，表明亟需专门面向多模态数据设计的安全防护。An adaptive and automatic data extraction attack procedure operating in a black box setting against MRAG, a configuration in which the retrieved visual artifact is itself the response, and shows the urgent need for safeguards specifically designed for multimodal data.

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.

MatRAG 在检索质量上优于其最强的竞争者；同时，通过避免 KG 构建和基于 LLM 的摘要降低了索引成本，并通过维度感知的相似度降低了查询成本。MatRAG outperforms its strongest competitors in terms of retrieval quality; furthermore, it reduces indexing costs by avoiding KG construction and LLM-based summarization, and lowers query-time costs through dimension-aware similarity.

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.

在 Encyclopedic-VQA 和 InfoSeek 上的实验表明，CLIMB 持续优于基于检索增强的多模态基线；消融实验显示互补池化、基于评论家的打分以及迭代置信度控制的精炼各自对最终性能均有贡献。Experiments on Encyclopedic-VQA and InfoSeek show that CLIMB consistently improves over retrieval-augmented multimodal baselines, andlations indicate that complementary pooling, critic-based scoring, and iterative confidence-controlled refinement each contribute to the final performance.

本文在桌游《The Dark Eye》的虚构世界之上构建了一个完全单语德语的 RAG 问答测试平台——该领域德语资料丰富但过于小众，模型无法凭记忆作答，必须依赖检索。This work builds a fully monolingual German RAG question-answering testbed over the fictional world of the tabletop role-playing game The Dark Eye, a domain that is richly documented in German but too niche for the model to answer from memory, so that it has to rely on retrieval.

提出 AI 决策检查点——过程开发轨迹中的显式时刻，过程开发者在此识别 AI 候选子过程，评估对时间、成本、质量与灵活性的预期影响，考虑法律与组织约束，并记录关于采用、限制或拒绝特定 AI 组件的合理决策。AI-decision checkpoints are proposed, explicit moments in a process development trajectory where process developers identify AI-candidate sub-processes, assess expected effects on time, cost, quality, and flexibility, consider legal and organisational constraints, and document a reasoned decision to adopt, constrain, or reject specific AI components.

提出一种"失败即关闭"的临时可见性协议：在截止时间前接纳新内容，隐藏验证未及时提交的项目，并支持按谱系范围的遏制，同时量化新鲜度与可用性之间的权衡。A fail-closed provisional-visibility protocol is presented that admits new content under a deadline, hides items whose verification has not committed in time, and supports lineage-scoped containment, and quantifies the freshness and availability trade-offs.

DynaKRAG 是一种统一的证据-动作框架,通过学习共享的状态条件策略来协调上述操作,证明统一的状态条件证据控制能在保证强回答质量的同时,实现高效检索与紧凑的答案生成上下文。DynaKRAG, a unified evidence-action framework that learns a shared state-conditioned policy for coordinating these operations, demonstrates that unified, state-conditioned evidence control supports strong answer quality, efficient retrieval, and compact answer-generation contexts.

当前大视频语言模型（LVLM）在处理长视频时仍面临挑战，主要原因是帧通常被独立处理，难以捕获跨事件的时序依赖。尽管检索增强方法已被引入以提供额外上下文，但多数方法在帧或片段层面操作，限制了建模事件随时间演化及其相互关系的能力。本文提出事件链检索增强生成（EC-RAG），一种无需训练的框架，将视频内容组织为 ex...Current large video-language models (LVLMs) still face challenges when dealing with long videos, mainly because frames are often processed independently, making it difficult to capture temporal dependencies across events. Although retrieval-augmented approaches have been introduced to provide additional context, most of them operate at the frame or snippet level, which limits their ability to model how events evolve over time and relate to each other. In this paper, we propose Event Chain Retrieval-Augmented Generation (EC-RAG), a training-free framework that organizes video content into an ex

结果显示，RAG 在生成完整 API 调用时能够减少幻觉并提升正确性，但在端点已提供的情况下反而会促使生成不必要的参数而降低正确性；约束解码（CD）则能可靠地防止非法 URL、HTTP 方法与参数的出现，并显著提升两种 starter code 的整体正确性。Results show that RAG reduces hallucinations and improves correctness when generating full API invocations but reduces it when the endpoint is already provided as it encourages the generation of unnecessary parameters, and CD reliably prevents illegal URLs, HTTP methods, and arguments and substantially improves overall correctness for both starter codes.

检索增强生成（RAG）系统易遭受嵌入在检索内容中的提示注入攻击。我们提出 RAG-PIBench，一个面向 RAG 风格提示注入检测的基准，包含跨冻结训练、验证与受保护测试划分的 4,876 个上下文示例。基于泄露感知构建流水线与严格评估协议，我们对比了基于关键词、语义引用、TF-IDF 与 Transformer 的检测器。DistilBERT 在受保护测试集上取得最佳性能（F1=0.896，PR-AUC=0.968），而 TF-IDF SVM 与逻辑回归仍具竞争力...Retrieval-Augmented Generation (RAG) systems are vulnerable to prompt-injection attacks embedded in retrieved content. We introduce RAG-PIBench, a benchmark for RAG-style prompt-injection detection containing 4,876 contextual examples across frozen train, validation, and protected-test splits. Using a leakage-aware construction pipeline and strict evaluation protocol, we compare keyword-based, semantic-reference, TF-IDF, and transformer-based detectors. DistilBERT achieves the best protected-test performance (F1 = 0.896, PR-AUC = 0.968), while TF-IDF SVM and logistic regression remain competit

长上下文推理与检索增强生成（RAG）在截然不同的规模上处理证据选取——从单个长 prompt 到整个语料库。我们探究是否存在一种模型内部机制能够跨该范围选取证据。提出 UNREAL（UNifying REtrieval And Long-Context with a Single Model），一种模型原生的证据选取框架，跨越语料检索与长上下文推理。UNREAL 直接从冻结 LLM 的内部表征中编码 chunk 并推导检索查询，新增可训练参数少于 500K，且保持基模型...Long-context inference and Retrieval-Augmented Generation (RAG) handle evidence selection at vastly different scales, from a single long prompt to an entire corpus. We ask whether a single model-internal mechanism can select evidence across this range. We introduce UNifying REtrieval And Long-Context with a Single Model (UNREAL), a model-native evidence selection framework to span corpus retrieval and long-context inference. UNREAL encodes chunks and derives retrieval queries directly from the frozen LLM's internal representations. It adds fewer than 500K trainable parameters and leaves the ba

论文提出 Agentic AutoRAG，一个面向多目标 RAG 超参数优化并具备检索-生成失败归因能力的 LLM Agent 优化器，其 LLM-judge 准确率高于作者对比的全部基线，并在前 10 次试验中达到或超过统计基线 30 次试验的 judge 准确率。Agentic AutoRAG is introduced, an LLM-agent optimizer for multi-objective RAG hyperparameter optimization with retrieval-versus-generation failure attribution, and reaches higher LLM-judge accuracy than every baseline the authors compare, and within its first 10 trials it matches or beats the statistical baselines' full 30-trial judge accuracy.

本文研究仅使用身份标签对预训练关键点匹配器进行弱监督自适应，无需关键点级或几何对应真值，并利用典型监测数据集中已有的身份标注，实现图像匹配模型向野生动物领域的数据高效专业化。This work studies weakly supervised adaptation of a pretrained keypoint matcher using only identity labels, without keypoint-level or geometric correspondence ground truth, and enables data-efficient specialization of image matching models to wildlife domains using identity annotations already available in typical monitoring datasets.

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.

大语言模型正日益应用于基于长且异构信息源的任务。传统 RAG 依赖固定的相似度检索，而 agentic 变体虽能自适应查询与工具使用，但仍以检索为中心。然而在许多任务中，解答所需的证据并未显式存在于任何单一来源条目中，而必须通过对多个来源条目进行过滤、聚合或计算来推导。在本工作中，我们提出 RECAST（通过计算、访问与综合进行证据路由）……（原文截断）Large language models are increasingly applied to tasks grounded in long, heterogeneous information sources. Conventional Retrieval-Augmented Generation (RAG) relies on fixed similarity-based retrieval, while agentic variants adapt queries and tool use but remain largely retrieval-centric. However, in many tasks, the evidence required for a solution is not explicitly present in any single source item. Instead, it must be derived through filtering, aggregation, or computation across multiple source items. In this work, we introduce RECAST (Routing Evidence through Computation, Access, and Synth

DeepSeek Engram 等条件记忆架构利用输入 n-gram 查询已学习的 embedding，以有限的额外计算扩展大语言模型（LLM）容量。除模型扩展外，该架构还展现出将事实知识存储与通用计算解耦的潜力，为在固定 Transformer 主干的同时更新事实知识提供了一条可行路径。然而实现这一目标颇具挑战：同一事实的不同表达可能激活不同的 n-gram embedding，而更新共享 embedding 又会……Conditional memory architectures such as DeepSeek Engram use input n-grams to look up learned embeddings, expanding the capacity of large language models (LLMs) with limited additional computation. Beyond model scaling, this architecture has demonstrated the potential to decouple factual knowledge storage from general-purpose computation, offering a promising route to updating factual knowledge while keeping the Transformer backbone fixed. Realizing this potential is challenging because different expressions of a fact may activate different n-gram embeddings, while updating shared embeddings c

检索增强生成系统日益依赖文档结构处理：结构对齐分块、LLM 生成的块上下文、标题路径元数据，以及分层两阶段检索。各自研究在不同语料、嵌入器和指标上支持各自方法，但没有一项控制了共同混杂因素：在块前添加任何文本都会扰动其嵌入。我们提出机制隔离的消融方法，在同一协议下测试全部四种处理，跨条件匹配块大小，并加入一个语义为空的安慰剂——结构上有效但被打乱Retrieval-augmented generation systems increasingly rely on document-structure treatments: structure-aligned chunking, LLM-generated chunk contexts, heading-path metadata, and hierarchical two-stage retrieval. Separate studies support each on different corpora, embedders, and metrics, and none control for a shared confound: any text prepended to a chunk perturbs its embedding. We present a mechanism-isolating ablation testing all four treatments under one protocol, matching chunk sizes across conditions and adding a semantically null placebo---heading paths that are structurally valid but shuf