AI Agent

Tool-R1: Sample-Efficient Reinforcement Learning for Agentic Tool Use

Yabo Zhang, Yihan Zeng, Qingyun Li, Zhen Hu, Kavin Han, Wangmeng Zuo

机构 * Harbin Institute of Technology（哈尔滨工业大学） ； Huawei Noah’s Ark Lab（华为诺亚实验室） 纠错

专题命中 工具调用 ：tool use(title,abstract)；agentic(title)；分类 cs.LG

Scaling Agents via Continual Pre-training

Liangcai Su, Zhen Zhang, Guangyu Li, Zhuo Chen, Chenxi Wang, Maojia Song, Xinyu Wang, Kuan Li, Jialong Wu, Xuanzhong Chen, Zile Qiao, Zhongwang Zhang, Huifeng Yin, Shihao Cai, Runnan Fang, Zhengwei Tao, Wenbiao Yin, Chenxiong Qian, Yong Jiang, Pengjun Xie, Fei Huang, Jingren Zhou

专题命中 工具调用 ：agent(abstract,comments)；tool use(abstract)；tool-use(abstract)；agentic(abstract)

Comments https://tongyi-agent.github.io/blog/introducing-tongyi-deep-research/

Auditable Early Stopping for Agentic Routing: Ledger-Verified Run-Wise Certificates under Local DP

Shivam Akhauri

专题命中 工具调用 ：agentic(title)；tool-use(abstract)；分类 cs.LG

MillStone: How Open-Minded Are LLMs?

Harold Triedman, Vitaly Shmatikov

机构 * Cornell Tech（康奈尔科技） 纠错

专题命中 工具调用 ：agentic(abstract)；分类 cs.CL、cs.LG

Comments 19 pages, 7 tables, 7 figures

TAPS: Tool-Augmented Personalisation via Structured Tagging

Ekaterina Taktasheva, Jeff Dalton

专题命中 工具调用 ：tool use(abstract)；分类 cs.CL

Comments Accepted to EMNLP 2026 Main

Robust Contracting for Sequential Search

Théo Durandard, Udayan Vaidya, Boli Xu

专题命中 工具调用 ：agent(abstract)