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 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…

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…

The paper introduces Trajectory-aware OPD (TOPD), a method that uses near-future trajectory information to improve On-Policy Distillation by accurately identifying and guiding true reasoning divergenc…

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

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 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…

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

This paper introduces RREDCoT, a method for approximating optimal reward redistribution in Chain-of-Thought reasoning language models without additional generation.

This paper introduces RREDCoT, a method for approximating optimal reward redistribution in Chain-of-Thought reasoning language models without additional generation.

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

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 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…

The paper introduces Canonical-Context On-Policy Distillation (CCOPD) to improve multi-turn language model performance by mitigating 'self-anchored drift,' ensuring consistent answers regardless of wh…

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

This paper investigates the non-monotonic role of sample difficulty in Reinforcement Learning with Verifiable Reward (RLVR), finding that medium-difficulty problems provide the most balanced and benef…

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…