ACM Transactions on Software Engineering and Methodology · 2026-10-30 · 期刊论文
Automated program repair has traditionally focused on single-hunk defects, overlooking multi-hunk bugs that are prevalent in real-world systems. Repairing these bugs requires coordinated edits across multiple, disjoint code regions, posing substantially greater challenges. We present the first systematic study of LLM-driven coding agents ( Claude Code, Codex, Gemini-cli , and Qwen Code ) on this task. We evaluate the…
(中文解读待补写)
🔗 打开原文
Noor Nashid, Daniel Ding, Keheliya Gallaba 等
本文摘自《每日前沿研究简报 · 2026-11-01》「AI 科研智能体 / AI 科学家」。本内容仅用于研究信息整理与科普交流,不构成医疗建议。

发表评论 取消回复