AI 大模型

AI Agent

智能体、工具调用、规划、工作流、多智能体和自主任务执行。

2025-10-28 至 2025-10-28 共收录 160 篇信号源：cs.AI, cs.CL, cs.LG, cs.SE

1. Agent评测 25 篇

2505.21347 2025-10-28 cs.LG 57%

OVERT: A Benchmark for Over-Refusal Evaluation on Text-to-Image Models

Ziheng Cheng, Yixiao Huang, Hui Xu, Somayeh Sojoudi, Xuandong Zhao, Dawn Song, Song Mei

机构 * UC Berkeley（加州大学伯克利分校）

专题命中 Agent评测：workflow(abstract)；分类 cs.LG

Comments NeurIPS 2025 (D&B Track)

2510.22045 2025-10-28 cs.CV cs.AI 57%

VLM-SlideEval: Evaluating VLMs on Structured Comprehension and Perturbation Sensitivity in PPT

Hyeonsu Kang, Emily Bao, Anjan Goswami

专题命中 Agent评测：agentic(abstract)；分类 cs.AI

Comments 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop: Evaluating the Evolving LLM Lifecycle - Benchmarks, Emergent Abilities, and Scaling

2510.23190 2025-10-28 cs.CV 50%

Evaluation of Vision-LLMs in Surveillance Video

Pascal Benschop, Cristian Meo, Justin Dauwels, Jelte P. Mense

机构 * Department of Computer Science（计算机科学系）； Delft University of Technology（代尔夫特理工大学）； LatentWorlds AI ； National Policelab AI & Model-Driven Decisions Lab（国家警务实验室AI与模型驱动决策实验室）

专题命中 Agent评测：agent(abstract)

Comments Accepted as poster in the NeurIPS 2025 Workshop on Space in Vision, Language, and Embodied AI

2510.22670 2025-10-28 cs.IR 50%

Tools are under-documented: Simple Document Expansion Boosts Tool Retrieval

Xuan Lu, Haohang Huang, Rui Meng, Yaohui Jin, Wenjun Zeng, Xiaoyu Shen

专题命中 Agent评测：tool use(abstract)

2510.19462 2025-10-28 cs.CR 50%

AegisMCP: Online Graph Intrusion Detection for Tool-Augmented LLMs on Edge Devices

Zhonghao Zhan, Amir Al Sadi, Krinos Li, Hamed Haddadi

专题命中 Agent评测：agent(abstract)

2110.13543 2025-10-28 physics.soc-ph cs.MA q-bio.QM 50%

Collective decision-making under changing social environments among agents adapted to sparse connectivity

Richard P. Mann

专题命中 Agent评测：agent(abstract)

2. 其他Agent 4 篇

2507.10741 2025-10-28 cs.LG cs.AI 76%

Ground-Compose-Reinforce: Grounding Language in Agentic Behaviours using Limited Data

Andrew C. Li, Toryn Q. Klassen, Andrew Wang, Parand A. Alamdari, Sheila A. McIlraith

机构 * Department of Computer Science, University of Toronto（计算机科学系，多伦多大学）； Vector Institute for Artificial Intelligence（人工智能矢量研究所）； Schwartz Reisman Institute for Technology and Society（技术与社会施瓦茨-雷曼研究所）

专题命中其他Agent ：agentic(title)；分类 cs.AI、cs.LG

Comments NeurIPS 2025

2510.22084 2025-10-28 cs.CL 57%

Compositional Bias Control in Large Language Models: Preference Learning Fails, Supervision Succeeds

Atij Mahesh

机构 * University of California, Los Angeles（加州大学洛杉矶分校）

专题命中其他Agent ：agentic(abstract)；分类 cs.CL

Comments 20 pages

2510.22105 2025-10-28 cs.SD 50%

Streaming Generation for Music Accompaniment

Yusong Wu, Mason Wang, Heidi Lei, Stephen Brade, Lancelot Blanchard, Shih-Lun Wu, Aaron Courville, Anna Huang

机构 * Mila, Quebec Artificial Intelligence Institute, Université de Montréal（魁北克人工智能研究所，蒙特利尔大学）； MIT - Massachusetts Institute of Technology（麻省理工学院）； Canada CIFAR AI Chair（加拿大 CIFAR 人工智能 chair）

专题命中其他Agent ：agentic(abstract)

2510.22098 2025-10-28 cs.HC 50%

Beyond Reality: Designing Personal Experiences and Interactive Narratives in AR Theater

You-Jin Kim

专题命中其他Agent ：AI agent(abstract)

Comments PhD Thesis, Media Arts and Technology, University of California, Santa Barbara, defended on December 13, 2024. Available from ProQuest Dissertations & Theses Global (Order No. 31761773). This version is shared on arXiv for broader accessibility