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
In latest · #157 Added on 2026-10-21
One-line takeaway
Trains category-specific SWE experts and then integrates them, easing the see-saw across task categories in pooled RL.
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。
Read on arXiv PDF Hugging Face discussion Code Project page
Topics & disciplines
More on Code & SWE
- 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
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.