arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

期刊&会议

International Conference on Learning Representations · 会议 · Machine Learning

2025-09-12 至 2025-09-12 共收录 1
2509.09265 2025-09-12 cs.LG cs.CL

Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents

Jiawei Wang, Jiacai Liu, Yuqian Fu, Yingru Li, Xintao Wang, Yuan Lin, Yu Yue, Lin Zhang, Yang Wang, Ke Wang

机构 * ByteDance Seed(字节跳动种子)

Comments ICLR 2026 Under review

详情

展开后加载摘要…

URL PDF HTML 收藏