cs.SE · 2026-08-09 · No. 79
Software Engineering, 2026-08-09.
2 new papers in cs.SE. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
2 entries-
01
Learning Globally Reusable Skills for Coding Agents
Chen Yang, Jiashuo Tian, Ziqi Wang, Xinyin Liu, Meiru Ye, Junjie Chen
cs.SE · cs.AI
Automated skill evolution enables Large Language Model (LLM) agents to continuously improve without expensive retraining. However, existing approaches typically treat skill evolution as a sequence of local updates, overlooking relationships among skills and often producing overfitted skill updates that fail to generalize across tasks. We propose GSE, a globalized skill evolution framework that jointly optimizes skill compatibility and skill...
-
02
CodeGrep: An RL-Trained Retrieval Agent for LLM Coding Agents
Wuya Chen, Yihao yang, Yang Cao, Yue Lin
cs.SE · cs.AI
Modern LLM coding agents such as Claude Code and OpenHands share a common inefficiency: they spend much of their token budget finding the file to patch, rather than patching it. On SWE-Bench Verified, a 30B OpenHands agent averages 23 rounds and 631K tokens per resolved issue, with many calls spent on grep, glob, and view_file during repository exploration. We introduce CodeGrep, a 14B retrieval agent trained end-to-end with GRPO to issue...
This edition is part of The Daily Abstract — cs.SE archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.