MetaAgent-X uses end-to-end RL to jointly optimize automatic multi-agent system design and execution, outperforming baselines by up to 21.7% through hierarchical rollouts and stagewise co-evolution.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning
MetaAgent-X uses end-to-end RL to jointly optimize automatic multi-agent system design and execution, outperforming baselines by up to 21.7% through hierarchical rollouts and stagewise co-evolution.