The paper introduces REFT, a novel method that diversifies rollouts by sampling the first token after the reasoning marker, significantly improving performance in Reinforcement Learning with Verifiabl…

The paper demonstrates that using Reinforcement Learning from Verifiable Rewards (RLVR) significantly improves small language models' functional correctness in code generation, particularly when combi…

The paper proposes Credit-Attenuated Privileged Feedback (CAPF), a training-time mechanism that uses verifier-side information to guide LLM search agents, significantly improving their performance on…

The paper introduces Group Prioritized Off-Policy Optimization (POPO), a novel framework that efficiently accelerates RL finetuning for LLM reasoning by leveraging effective off-policy training batche…

The paper introduces $ ext{RLR}^3$, a novel framework that extends verifiable rewards in Reinforcement Learning to handle partially verifiable, multi-criteria vision-language tasks by integrating robu…

This paper proposes a new imitation learning algorithm called DistIL that uses distributional feedback to improve policy improvement and regret guarantees.

The paper introduces Cross-Model Entropy (CME), a novel label-free reward signal that uses an independent verifier model to assess the quality of a generator's output, significantly improving LLM perf…

The paper proposes CAST, an answer-free self-distillation method that enhances Group Relative Policy Optimization (GRPO) for verifiable rewards, allowing token-level advantage signals even when all sa…

DenoiseRL is a novel reinforcement learning framework that improves reasoning in large language models by optimizing directly from the failures and incorrect reasoning traces of weak models, eliminati…

The paper introduces Contrastive Reflection (CORE), a novel non-parametric method that rapidly improves language model reasoning by distilling contrasts between successful and unsuccessful problem att…

The paper proposes LaRA, a layer-wise representation analysis framework that detects data contamination in RL post-trained LLMs by analyzing geometric deviations across model layers.

The paper introduces Feedback Distillation, a novel training method that uses a language model's privileged feedback to provide token-level supervision, significantly improving complex reasoning tasks…

DRIFT proposes a novel framework that efficiently optimizes LLMs for multi-turn interactions by decoupling rollout from optimization, allowing the use of weighted supervised fine-tuning to match the p…

The paper introduces SAVE, a framework that uses on-policy feedback and the value function to self-supervise and improve reward models, significantly enhancing RLHF performance across multiple benchma…

ZipRL introduces an adaptive context compression framework that significantly improves the performance and efficiency of LLMs in complex, multi-turn agent tasks by combining multi-granularity compress…

ARES is a novel framework that systematically discovers and mitigates dual vulnerabilities in RLHF systems by simultaneously testing the core LLM and its Reward Model (RM) using structured adversarial…

This paper introduces a novel backdoor attack (ACB) against Reinforcement Learning with Verifiable Rewards (RLVR), demonstrating that poisoning the training data can implant a backdoor that significan…

This paper proposes using offline reinforcement learning (RL) as an efficient alternative to online RL for post-training code-generating LLMs, demonstrating its effectiveness, especially for smaller m…

The paper proposes Skill-RM, a unified framework that treats reward modeling as an agentic task to consistently integrate diverse evaluation criteria, achieving superior performance over traditional m…

The paper introduces Prompted Policy Optimization (PromptPO), an LLM-based method that successfully optimizes policies for various sequential RL tasks, demonstrating that LLMs can replace classical RL…