论文

本文发现视觉提示工程（visual prompt engineering，简称 VIPE）能在多项任务上提升视频推理性能，甚至比经典的文本提示工程或 test-time scaling 更有效。It is found that visual prompt engineering, or VIPE for short, improves video reasoning performance across tasks and can be even more effective than classic text-based prompt engineering or test-time scaling.

本文在由专家级 MITRE Center for Threat-Informed Defense 标注构成的、包含 1,207 条 CVE 的精选 gold 数据集上训练多标签分类器，结果表明该分类器受限于标签质量而非数据规模。A multi-label classifier is trained on a curated gold dataset of 1,207 CVEs from expert MITRE Center for Threat-Informed Defense mappings, indicating that the classifier is limited by label quality rather than dataset size.

本文提出 RARG（Relevance-Aware RipGrep Search Agent），将相关性转化为 corpus 交互的执行先验，并证明相关性感知交互可带来更快且更可靠的搜索收敛。The Relevance-Aware RipGrep Search Agent (RARG) is introduced, which turns relevance into an execution prior for corpus interaction, and demonstrates that relevance-aware interaction enables faster and more reliable search convergence.

本文提出 InMind，一项包含 125 个任务、经专家校验、跨越十个生活领域的基准，其中 113 个任务基于可引用的公开来源；本文将此类失效模式命名为 implicit-association blind spot，并提出一种极简诊断探针（diagnostic probe），在 query 到达前保持 memory 可见即可恢复大部分性能差距。This work introduces InMind, a 125-task, expert-verified benchmark spanning ten life domains, with 113 tasks grounded in citable public sources, and calls this failure mode the implicit-association blind spot, and introduces a minimal diagnostic probe that keeps memory visible before the query arrives recovers most of the gap.

本文提出 Mage-VL，一种面向实时多模态理解与交互的高效 codec-native 流式基础模型，并构建了 AI4AI 数据流水线，涵盖面向多模态 captioning 的 prompt-code 联合优化与以 AI 驱动的性能诊断，以指导训练方案。Mage-VL is presented, an efficient codec-native streaming foundation model for real-time multimodal understanding and interaction and establishes AI4AI data pipelines encompassing prompt-code joint optimization for multimodal captioning and AI-driven performance diagnosis to guide training recipes.

PerceptionBench 通过诊断前沿 MLLMs 在 42 项现有基准上响应中的最早失效点，并构建一个感知分支定义十种原子感知能力的错误分类法，为衡量与诊断 MLLMs 视觉感知边界提供了一项能力级（capability-level）标准。PerceptionBench provides a capability-level standard for measuring and diagnosing the visual perception boundaries of MLLMs, by diagnosing the earliest failure points in the responses of frontier MLLMs across 42 existing benchmarks and constructing an error taxonomy whose perception branch defines ten atomic perceptual capabilities.

本文综述了该边界上的五类漏洞：多步攻击链、与沙箱边界冲突的目标、供应链与凭据暴露、持续性的 command-and-control，以及自动化行动的速度。This review synthesizes five vulnerability classes at that boundary: multi-step offensive chains, objectives that conflict with sandbox boundaries, supply-chain and credential exposure, persistent command-and-control, and the speed of automated action.

本文提出 Kontrast，一种利用 Text-to-SPARQL 与 LLM 推理将基于表格的答案与 KG 证据进行对比并对所产生的不一致性进行分类的自动框架，并表明文本、表格与 KG 可通过系统性对比相互补充与纠错。Kontrast is presented, an automatic framework that uses Text-to-SPARQL and LLM reasoning to compare table-based answers with KG evidence and categorize the resulting inconsistencies, and shows that text, tables, and KGs can complement and correct one another through systematic comparison.

BeyondUncertainty 首先引出结构化的临时答案与置信度估计，然后应用在 held-out 验证数据上选定并在测试评估前冻结的模型特定阈值，揭示了更具选择性的证据获取与端到端 token 效率之间的权衡。BeyondUncertainty first elicits a structured provisional answer and confidence estimate, then applies a model-specific threshold selected on held-out validation data and frozen before test evaluation, revealing a trade-off between more selective evidence acquisition and end-to-end token efficiency.

介绍 RepoReasoner，一个用于评估仓库级代码推理的 benchmark，评估两种互补能力：Output Prediction，衡量跨文件的细粒度、有状态执行推理；Call Chain Prediction，在噪声上下文下评估高层架构依赖理解。RepoReasoner is introduced, a benchmark for evaluating repository-level code reasoning that assesses two complementary abilities: Output Prediction, which measures fine-grained, stateful execution reasoning across files, and Call Chain Prediction, which evaluates high-level architectural dependency understanding under noisy context.

这些结果共同支持多视角的仓库上下文服务，在仓库上下文全生命周期中提供显式的、面向操作的有效性边界以及质量-成本前沿。Together, these results support multi-view repository-context serving with explicit, operation-specific validity boundaries with quality-cost frontiers across the repository-context lifecycle.

介绍 Parallel Decoding Distillation，一种简化且可扩展的基于轨迹的蒸馏方法，用于 diffusion 和 flow matching 模型的快速推理，并显著提升生成视频的多样性。Parallel Decoding Distillation is introduced, a simplified and scalable trajectory-based distillation method for fast inference of diffusion and flow matching models and presents a significant improvement in generated video diversity.

介绍 VisualPatchWorld，将世界动态表示为代码，先通过短时主动探查选择定性动力学形式，再通过最小化多步预测误差，从记录的状态-动作轨迹中拟合该形式的自由参数。VisualPatchWorld is introduced, which represents world dynamics as code and first selects a qualitative dynamical form with short active probes, then fits that form's free parameters from recorded state-action traces by minimizing multi-step prediction error.

Temporal-Distance-JEPA 通过发现离线日志中的时间进展结构，并将代价形式与规划时部署协同设计，缩小了 JEPA world-model 规划器的训练-规划差距。Temporal-Distance-JEPA narrows the train--plan gap for JEPA world-model planners by discovering temporal progress structure in offline logs and co-designing cost form with plan-time deployment.

本文提出基于双向 Mamba 块（Vim）的通用视觉 backbone，通过位置嵌入标记图像序列，并利用双向 state space model 压缩视觉表征，具有成为下一代视觉基础模型 backbone 的巨大潜力。This paper proposes a new generic vision backbone with bidirectional Mamba blocks (Vim), which marks the image sequences with position embeddings and compresses the visual representation with bidirectional state space models and has great potential to be the next-generation backbone for vision foundation models.

本文提出 embodied language model，将真实世界连续传感器模态直接融入语言模型，从而建立词语与感知之间的联系，实现真实世界中的通用推理。This work proposes embodied language models to directly incorporate real-world continuous sensor modalities into language models and thereby establish the link between words and percepts to enable general inference in the real world.

本文提出极简的预训练框架 SimVLM，在广泛的判别式与生成式视觉-语言基准上显著超越既往预训练方法并取得新 SOTA，包括 VQA、NLVR2 以及图像描述任务。This work presents a minimalist pretraining framework, named SimVLM, which significantly outperforms previous pretraining methods and achieves new state-of-the-art results on a wide range of discriminative and generative vision-language benchmarks, including VQA, NLVR2, and image captioning tasks.

介绍 HANDBOOK_md，一个包含 65 个 agentic 任务的 benchmark，模拟员工遵循公司手册的方式；每项任务对 10 份基础手册之一进行修改，变动评分所依赖的具体规则和阈值，因此没有任何两个任务共享同一套策略。HANDBOOK_md is presented, a benchmark of 65 agentic tasks modeled on how employees follow company handbooks, and every task modifies one of 10 base handbooks, altering the specific rules and thresholds on which grading depends, so no two tasks share the same set of policies.

本文研究无人机（UAV）可见光-近红外（VNIR）高光谱图像中 PFM-1 地雷的检测，使用光谱角制图（SAM）、匹配滤波器（MF）、自适应相干估计器（ACE）和约束能量最小化（CEM）。This paper studies PFM-1 landmine detection in unmanned aerial vehicle (UAV) visible and near-infrared (VNIR) HSI using spectral angle mapper (SAM), matched filter (MF), adaptive coherence estimator (ACE), and constrained energy minimization (CEM).

一项受控的种子干预实验发现，与随机非 gold 上下文相比，由检索得到的初始上下文以更少的后续探索取得更高的文件 F1，而 oracle gold 上下文仍存在可观的提升空间。A controlled seed-intervention pilot finds that retrieval-derived initial context yields higher file F1 with less post-seed exploration than random non-gold context, while oracle gold context shows substantial remaining headroom.

基于 ONNX Runtime 的原生 C++ 推理引擎击败了所有 baseline，置信区间甚至不重叠；batch 策略的影响比语言或运行时的选择更关键，超出作者预期。A native C++ inference engine on ONNX Runtime that beat every baseline, confidence intervals didn't even overlap, and batching strategy mattered more than either the language or the runtime choice, more than the authors expected.

本文提出 Metis，首个 memory foundation model 原型，赋予 foundation model 原生记忆能力，并表明原生记忆在架构、端到端优化和效率方面具有优势。This paper proposes Metis, the first prototype of memory foundation models, which empower foundation models with native memory capabilities and shows that native memory offers advantages in architecture, end-to-end optimization, and efficiency.

跨任务的测试时扩展实验表明，SkillRise 跨任务复用可迁移的 skill，而非受益于对同一任务的重复采样，在保持强性能的同时显著降低多阶段 skill 学习流水线的运行时开销。Scaling at test time across tasks suggests that SkillRise reuses transferable skills across tasks rather than benefiting from repeated sampling of the same task, and retains strong performance while substantially reducing the runtime overhead of skill learning pipelines with multiple stages.

介绍 DecoEvo（Decoupled Co-Evolution），在解耦目标下协同进化一个求解器 skill 和一个 rubric 生成器 skill，优化过程中不使用 gold rubric。DecoEvo (Decoupled Co-Evolution), which co-evolves a solver skill and a rubric-generator skill under decoupled objectives without using gold rubrics during optimization, is introduced.

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 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.