Replacing GRPO's fixed clipping range with a task-wise entropy-aware adaptive bound stabilizes multi-task agentic LLM training by synchronizing exploration-exploitation paces.
Agenttuning: Enabling generalized agent abilities for llms
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Entropy Pacing Policy Optimization for Multi-Task Agentic Reinforcement Learning
Replacing GRPO's fixed clipping range with a task-wise entropy-aware adaptive bound stabilizes multi-task agentic LLM training by synchronizing exploration-exploitation paces.