cs.SE · 2026-10-27 · No. 155
Software Engineering, 2026-10-27.
5 new papers in cs.SE. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
5 entries-
01
Ranking Function Generation with LLMs for Termination
Rongkang Li, Jiaxin Hu, Taolue Chen, Yong Li, Fu Song, Zhilin Wu
cs.SE · cs.AI · cs.LO
Ranking functions are a fundamental technique for proving loop termination, but constructing them manually is challenging and requires substantial expertise. We propose RAINFALL, a neuro-symbolic framework which follows the generate-verify-refine paradigm and tightly integrates LLMs with symbolic verification. RAINFALL formulates ranking function synthesis as a code-completion task by inserting placeholders into the input program and...
-
02
The Hidden Costs of Forgetting: A Study of Trajectory Deletion in Software Engineering Agents
Fernando Vallecillos-Ruiz, Islem Bouzenia, Michael Pradel, Leon Moonen
cs.SE · cs.AI
Software engineering agents resend their entire trajectory to an LLM at every turn, motivating online trajectory reduction. Prior work shows that randomly deleting 75% of tokens in old turns may preserve agent effectiveness, but it remains unclear why, how agents compensate for missing content, and whether it actually reduces costs. This paper presents an empirical study of 42 trajectory-reduction configurations, focusing on effectiveness,...
-
03
FeatureLoop: Benchmarking Coding Agents under Evolving Requirements
Jia Feng, Alyssa Wu, Cuiyun Gao, Yunlong Wang, Songyuanyi Lu, Zhichao Hu
cs.SE · cs.LG
Software development with coding agents often begins with a rough request that users refine after trying the implementation. Final correctness alone does not capture the repeated guidance this process requires. We introduce FeatureLoop, a benchmark of 61 human-reviewed tasks from 34 repositories across five primary programming languages and seven software forms. Each task follows one development goal in a persistent workspace through...
-
04
RepoTrace: Improving Requirement Tracing in Multi-Round Agent Interactions
Huanyu Liu, Yezheng Cheng, Jinliang You, Tianxiao Huang, Linyu Li, Zheng Fang, Peng Cao, Ge Li
cs.SE · cs.AI
Code agents have become increasingly capable of performing software engineering tasks through interaction with software environments. However, agents tend to degrade as the number of interaction rounds increases, making it difficult to maintain existing software during iterative modification. We analyze 2,656 agent trajectories in EvoCode-Bench and identify requirement focus misalignment as a recurring failure pattern, where agents struggle...
-
05
V$^3$AST-Bench: Verifiable, Valid, and Versatile Safety Evaluation for Coding Agents
Weitao Feng, Hengheng Xiong, Zihao Zeng, Jun Chen, Jiyang Guan, Xiaofeng Wang, Jialing Tao, Hui Xue, Wei Dong
cs.SE · cs.AI
Large language models increasingly act through code, modifying repositories, executing programs, and interacting with services in agent form. Their actions introduce risks that cannot be assessed from generated responses alone. Safety evaluation must verify actual consequences, distinguish harm avoidance from task incapability, and cover realistic workflows. We introduce V$^3$AST-Bench, a benchmark for Verifiable results, Valid...
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.