arXiv 2609.23377 · cs.SE · 2026-09-20
One to More, More to One: Category-Aware Iterative Expert Training for Software Engineering Agents
Jie Zhao, Ziyu Jiang, Suhang Zheng, Minghui Shan, Xiaoxiao Xu, Lin Qu
alibaba
在最新榜 #157 本站收录于 2026-10-21
一句话要点
按任务类别分别训练软件工程专家再合并，缓解统一 RL 训练中各类任务此消彼长的问题。
Trains category-specific SWE experts and then integrates them, easing the see-saw across task categories in pooled RL.
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：代码与软件工程
- CodeMidas: Scaling Agentic Coding RL Environments from Code Itself ▲138
- AesCode: Aesthetic Code Generation with Decoupled Cross-Modal Rewards ▲137
- LEGO-Anything: Coding Agents for 3D Scene Reconstruction ▲129
- 3DCodeVerse: Exploring 3D Worlds as Code ▲117
- Groupwise Agentic Grading and Advantage Redistribution for Code Agent RL ▲95
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。