arXiv 论文速递

We study decentralized partially observable team decision problems with low-rank latent dynamics and unknown system models. The proposed framework combines team-theoretic equivalen…

Long-term conversational memory in multi-party settings requires more than retrieving relevant content from long-term conversations: it must distinguish who said what, whom each st…

针对长时程编码智能体上下文超限问题，提出低成本压缩方法，直接缓解百万级 token 任务中的跨会话记忆瓶颈，实用性强。

Agents often work on complex problems that require millions of tokens of context, which necessitates compacting across sessions due to limited context windows. We develop CliffComp…

首个面向生产推理服务工程的智能体基准，填补了真实部署场景下智能体能力评估的空白，对推理系统与智能体落地都有直接价值。

We introduce SWE-Serve, a benchmark for evaluating agents on production inference engineering tasks. Implementing an inference feature can require coordinating multiple changes acr…

揭示 MCP 生态中基于语义匹配的工具选择存在供应链攻击面，提出轨迹优化的智能体劫持方法，对智能体安全与协议设计有重要警示意义。

Agents using the Model Context Protocol (MCP) rely on semantic matching to select tools from third-party servers, exposing a semantic supply-chain risk through attacker-controlled …

提出以可复用专家智能体替代重复上下文重建的框架演进思路，为降低长任务流中的冗余推理与成本提供了新范式。

Large language model (LLM) agents often handle streams of related tasks, yet standard harnesses repeatedly ask the model to reconstruct the same control decisions inside each task'…

Typed decision models are built for settings where model outputs are consumed directly by software. Instead of generating free-form text, they return a decision over a predefined s…

X-ray is medicine's most widely used imaging modality, yet remains among its least quantitative. Unlike volumetric modalities like CT or MRI, X-ray collapses 3D anatomy into a 2D p…

Large language models are increasingly used to generate SystemVerilog Assertions from natural-language specifica- tions and register-transfer-level designs. Existing datasets and b…

指出编译率等常用指标在漏洞修复评估中失效，并给出变更感知筛选方案，对 LLM 安全修复研究的评测可信度有纠偏意义。

Large language models (LLMs) are increasingly applied to the automated repair of C/C++ security vulnerabilities, and compile rate is a commonly reported proxy for progress: whether…

Clustering is an unsupervised learning technique that partitions unlabeled data into groups. Most existing methods require user-specified parameters, such as the number of clusters…

Detection of overlapping communities is essential for modelling networks in which nodes participate simultaneously in multiple structural or functional groups. Existing graph neura…