2 papers
cs.SE2026
MCPGen: Benchmarking LLMs on Executable MCPWorkflow Development
Yingxuan Yang, Jiaqi Liu, Lirui Guan +4
We study whether LLMs can produce executable workflow artifacts that remain consistent across graph structure, tool implementation, schema bindings, and runtime wiring. In this set…
cs.MA2026
SkillMAS: Skill Co-Evolution with LLM-based Multi-Agent System
Shuai Pan, Yixiang Liu, Jiaye Gao +7
Large language model (LLM) agent systems are increasingly expected to improve after deployment, but existing work often decouples two adaptation targets: skill evolution and multi-…