评分 7.3 · 来源：cs.AI updates on arXiv.org · 发布于 2026-04-08
评分依据：通过原子技能扩展编码Agent
arXiv:2604.05013v1 Announce Type: cross Abstract: Current LLM coding agents are predominantly trained on composite benchmarks (e.g., bug fixing), which often leads to task-specific overfitting and limited generalization. To address this, we propose a novel scaling paradigm that shifts the focus from task-level optimization to atomic skill mastery. We first formalize five fundamental atomic skills, code localization, code editing, unit-test generation, issue reproduction, and code review, that serve as the basis vectors for complex software engineering tasks. Compared with composite coding task