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…

EchoRL proposes a lightweight module to exploit valuable learning signals from advantage-degenerated rollouts in Reinforcement Learning with Verifiable Rewards (RLVR), significantly improving LLM post…

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 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…

The paper proposes Skill-Conditioned Gated Self-Distillation (SGSD), a novel framework that uses retrieved, potentially noisy skills to guide LLM reasoning, achieving state-of-the-art performance on m…

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 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…

The OISD framework improves language model reasoning by distilling on-policy predictive signals from the final output layer to intermediate representations, leading to substantial improvements on math…

QUBRIC introduces a co-design framework that simultaneously optimizes queries and rubrics, overcoming the bottleneck of vague rubrics derived from open-ended questions, leading to significant gains in…

The paper proposes Deep Research as Rubric (DR-rubric), a novel evidence-driven framework that treats rubric construction itself as a research problem to generate fine-grained, scalable reward signals…

The paper introduces Latent Reward Steering (LRS), an adaptive inference-time framework that implicitly improves the reasoning ability of LLMs by guiding the model's internal latent states based on a…

The paper proposes a coherent inverse reinforcement learning (IRL) method to improve large behavior models for robotic control, achieving superior sample efficiency and performance on complex sparse m…

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 introduces Temperature-Scaled On-Policy Self-Distillation (TS-OPSD), a novel method that internalizes temperature-based policy reheating into model parameters to combat entropy collapse in r…

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 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…

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…

OmniOPD introduces a logit-free, chunk-level distillation framework that improves on standard On-Policy Distillation by using semantic similarity and peak-entropy scheduling, achieving state-of-the-ar…

The paper proposes DIBS, a decoupled behavioral cloning approach that stabilizes inductive generalization in RL by separating task-specific policy learning from the evolution function, leading to impr…