arXiv 2609.38288 · cs.AI · 2026-09-29
AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks
Hongjin Qian, Chaofan Li, Kun Luo, Wenqing Wei, Jianlyu Chen, Shuqi Lu, Yuyang Hu, Hongwang Xiao 等 14 人
Beijing Academy of Artificial Intelligence
在最新榜 #95 本站收录于 2026-10-21
一句话要点
AREX-2 用机器学习和算法编程中的长程改进轨迹训练，让 Agent 在测试时反复反思、不断改进答案。
AREX-2 trains on long improvement trajectories from ML and algorithm tasks so agents iteratively refine solutions at test time.
阅读 arXiv 原文 PDF Hugging Face 讨论 代码仓库 项目页
主题与学科
同主题：智能体
- Raven: The Harness of Harnesses for Composable Agentic Intelligence ▲748
- False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents ▲642
- BizAgentBench: Unveiling Hidden Challenges in Deploying Long-Horizon Agents for Real-World Business ▲490
- Omni-IO Skills: Harnessing Your Agent Omni-Native ▲485
- Player-1: Learning to Play from Synthetic Experience ▲348
数据说明
元数据来自 arXiv API（已核实）；点赞来自 Hugging Face 每日论文；引用来自 Semantic Scholar。最近刷新 2026-10-22。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。