IGRPO allocates multi-turn LLM agent rollout budget proportional to intermediate-state information gain, inducing an exponentially tilted teacher distribution for policy optimization.
Asymptotic evaluation of certain markov process expectations for large time, i.Communications on pure and applied mathematics, 28 (1):1–47, 1975
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Information Gain-based Rollout Policy Optimization: An Adaptive Tree-Structured Rollout Approach for Multi-Turn LLM Agents
IGRPO allocates multi-turn LLM agent rollout budget proportional to intermediate-state information gain, inducing an exponentially tilted teacher distribution for policy optimization.