技术雷达TECH RADAR · GITHUB · ARXIV · HACKER NEWS

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

Xiaoxing Ren, Thomas Parisini, Andreas A. Malikopoulos

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 statement concerns, ho

Haobo Zheng, Tan Tang, Yan Chen

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 CliffCompaction, an autocompa

Trang Nguyen, Eulrang Cho, Bingqing Chen

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

Jennifer Williams, Dave Farris, Jeff Farris

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 metadata and outputs

Laizhen Li, Xuan Wang, Peicheng Zhao

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's context. We study

Laizhen Li, Jiarui Li, Juanjuan Zhao

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 set of options. By co

Yu Sun, Junhao Xu

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 projection, causing s

Victor Ion Butoi, Vivek Gopalakrishnan, John V. Guttag

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

FNU Aditi

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 the generated patch

Om Nepal, Sushant Aryal, Oluseyi Olukola

原文 · 讨论

原文 · 讨论

原文 · 讨论

原文 · 讨论

原文 · 讨论

原文 · 讨论

原文 · 讨论

原文 · 讨论

原文 · 讨论

原文 · 讨论