cs.SE · 2026-10-12 · No. 141
Software Engineering, 2026-10-12.
4 new papers in cs.SE. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
4 entries-
01
SWE-DeceptionBench: Benchmarking Deceptive Behaviors of LLMs Across the Software Development Lifecycle
Xiting Liu, Lin Yang, Yitong Zhang, Jia Li, Shi-Min Hu
cs.SE · cs.AI
Large Language Models (LLMs) are increasingly used throughout the software development lifecycle. This growing reliance on LLMs raises concerns about their trustworthiness, with deception posing a particularly important risk. Deceptive behavior takes the form of misleading responses or assistance in fabricating, concealing, or distorting information. To study this behavior, we introduce SWE-DeceptionBench, a benchmark for evaluating LLM...
-
02
ProgramGym: Scaling Training Environments for Long-Horizon Program Reproduction Agents
Chengyi Yang, Renxu Bao, Jue Hou, Zongpei Teng, Ziheng Wang, Yujie Lin, Chengsong Huang, Junnan Zhu, Delai Qiu,...
cs.SE · cs.AI · cs.CL
Coding agents are increasingly used to build programs from scratch as software engineers do rather than to resolve issues within a repository or to generate a repository from a given requirements document. However, scalable verifiable training environments that force agents to discover what is required and to decide how the system should be designed remain scarce. Moreover, existing agent workflows also cannot sustain long-horizon development...
-
03
AgentSWE: Can Coding Agents Build the Agent You Actually Want?
Jiahao Wang, Hongjin Qian, Yuyang Hu, Jiajun Zhang, Zheng Liu
cs.SE · cs.AI · cs.LG
As the production of software passes into the hands of software itself, coding agents are increasingly commissioned to build agents fitted to their users' own workflows. This delegation carries a quiet assumption, that the delivered agent will faithfully serve the requirement it was built for, rather than merely appear to. No existing benchmark tests that assumption. We introduce AgentSWE, a benchmark for agent software engineering spanning...
-
04
Agent4Spec: An LLM-based Agentic System to Optimize API Specifications through Automated Validation and Market Analysis
Yongjian Tang, Costel Moraru, Doruk Tuncel, Hanya Elhashemy, Steffen Klepke, Thomas Runkler
cs.SE · cs.AI
API specifications serve as critical documentation for modern software development, directly impacting integration efficiency and client code generation. While recent advancements have leveraged Large Language Models (LLMs) to generate initial specifications from source code, existing approaches treat this process as a one-time event - overlooking the needs for continuous validation, long-term maintenance, and market-driven evolution of these...
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.