CoEvolve improves LLM agent performance by 15-19% on AppWorld and BFCL benchmarks through mutual evolution of the agent and data distribution using feedback-driven task synthesis.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
CoEvolve: Training LLM Agents via Agent-Data Mutual Evolution
CoEvolve improves LLM agent performance by 15-19% on AppWorld and BFCL benchmarks through mutual evolution of the agent and data distribution using feedback-driven task synthesis.