Survey mapping RL techniques onto LLM training and highlighting gaps in value-based, off-policy, and bootstrapping methods.
arXiv preprint arXiv:2503.19612 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
fields
cs.LG 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
TrOPD stabilizes on-policy distillation for LLMs with trust-region learning, outlier estimation, and off-policy guidance, outperforming prior OPD methods on reasoning and code benchmarks.
Outcome-level RL with binary or composite rewards improves compositional generalization over supervised fine-tuning by avoiding overfitting to frequent training patterns.
citing papers explorer
-
Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning
Survey mapping RL techniques onto LLM training and highlighting gaps in value-based, off-policy, and bootstrapping methods.
-
Trust Region On-Policy Distillation
TrOPD stabilizes on-policy distillation for LLMs with trust-region learning, outlier estimation, and off-policy guidance, outperforming prior OPD methods on reasoning and code benchmarks.
-
Reinforcement Learning for Compositional Generalization with Outcome-Level Optimization
Outcome-level RL with binary or composite rewards improves compositional generalization over supervised fine-tuning by avoiding overfitting to frequent training patterns.