CurateEvo evolves executable data-curation code using failed agent trajectories, improving post-training performance by 3.2 and 2.7 points over baselines on labeled and wild data respectively.
Agentgym-RL: An open-source framework to train LLM agents for long-horizon decision making via multi-turn RL
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CurateEvo: Data-Curation Evolving for Agentic Post-Training
CurateEvo evolves executable data-curation code using failed agent trajectories, improving post-training performance by 3.2 and 2.7 points over baselines on labeled and wild data respectively.