SkillMAS couples skill evolution with multi-agent system restructuring in LLM agents through utility learning from traces, bounded refinement, and evidence-gated changes, achieving competitive results on manipulation, CLI, and retail tasks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.MA 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SkillMAS: Skill Co-Evolution with LLM-based Multi-Agent System
SkillMAS couples skill evolution with multi-agent system restructuring in LLM agents through utility learning from traces, bounded refinement, and evidence-gated changes, achieving competitive results on manipulation, CLI, and retail tasks.