Showing cs.SEShow all
2 papers · 1 filter
cs.SE2026
Skills That Don't Exist: A Large-Scale Study of Hallucinated Skill Recommendation in LLM Agents
Weifeng Yuan, Wenbo Guo, Feng Dong +2
LLM agents acquire new capabilities by downloading skills from open registries. Instead of browsing these catalogs manually, developers typically ask the agent to recommend and ins…
cs.SE2026
DevOps-Gym: Benchmarking AI Agents in Software DevOps Cycle
Yuheng Tang, Kaijie Zhu, Bonan Ruan +14
Even though demonstrating extraordinary capabilities in code generation and software issue resolving, AI agents' capabilities in the full software DevOps cycle are still unknown. D…