One to More, More to One: Category-Aware Iterative Expert Training for Software Engineering Agents
Category-aware expert training and distillation lift a software-engineering agent to 58–59% resolution on SWE benchmarks.
The paper proposes category-aware expert training and policy integration for repository-level software engineering agents, addressing uneven gains across task categories under pooled reinforcement learning. SWE Labeler builds evidence-grounded training pools, and same-origin experts alternate Agentic-miniRL with Refresh-Repair-Expand, reusing verified successful trajectories for repair supervised fine-tuning. Label-routed multi-teacher on-policy distillation consolidates experts into one student without external solution trajectories. The final policy scores 58.04% mean resolution on Pro-618 and 59.00% on SWE-bench Multilingual, up 5.39 and 2.78 points over the base model.
- Category-specific RL plus Refresh-Repair-Expand addresses uneven progress across SWE task types.
- SWE Labeler organizes pools; experts need no external model for trajectories.
- Multi-teacher on-policy distillation merges experts into one student policy.
- MOPD reaches 58.04% on Pro-618 and 59.00% on SWE-bench Multilingual.
- Gains over the base model are 5.39 and 2.78 percentage points.
From the original article
1 min read at huggingface.co
Repository-level software engineering (SWE) comprises heterogeneous task categories, whose progress under pooled agentic reinforcement learning can be uneven: gains in some categories coincide with regressions in others, while aggregate resolution obscures these changes. Motivated by this category see-saw, we develop a category-aware expert-training and policy-integration framework.
By Jie Zhao, Ziyu Jiang, Suhang Zheng · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.