One to More, More to One: Category-Aware Iterative Expert Training for Software Engineering Agents
A category-aware expert-training and policy-integration framework for repository-level software engineering that evaluates Pooled RL and Balanced RL, expert development, and single-model integration through aggregate and per-category resolution, the minimum category lift over each joint-RL baseline, and expert-gain rec...
Jie Zhao, Zi-Yu Jiang, Suhang Zheng et al.
· 0 citations