ReuseRL augments agentic RL with an MDL-based compression penalty on skill reuse, proves a PAC-Bayes bound, and reports higher in- and out-of-distribution success on ALFWorld, TextWorld-Cooking, and Countdown-Stepwise versus GRPO and round-length baselines.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Skill Reuse as Compression in Agentic RL
ReuseRL augments agentic RL with an MDL-based compression penalty on skill reuse, proves a PAC-Bayes bound, and reports higher in- and out-of-distribution success on ALFWorld, TextWorld-Cooking, and Countdown-Stepwise versus GRPO and round-length baselines.