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 and 6 more
Beijing Academy of Artificial Intelligence
In latest · #95 Added on 2026-10-21
One-line takeaway
AREX-2 trains on long improvement trajectories from ML and algorithm tasks so agents iteratively refine solutions at test time.
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。
Read on arXiv PDF Hugging Face discussion Code Project page
Topics & disciplines
More on Agents
- 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
About this data
Metadata from the arXiv API (verified); upvotes from Hugging Face Daily Papers; citations from Semantic Scholar. Last refreshed 2026-10-22.
The takeaway is written by AIMap from the abstract; the abstract itself is not reproduced — read the original.