Cited by: DAPO: An Open-Source LLM Reinforcement Learning System at Scale
47 citation edges inside this catalog. A title match is weaker evidence than an identifier match. Zero entries does not mean no citations on the web.
- MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory
arxiv:2601.03192· evidence: id - Reinforced Efficient Reasoning via Semantically Diverse Exploration
arxiv:2601.05053· evidence: id - Dr. Zero: Self-Evolving Search Agents without Training Data
arxiv:2601.07055· evidence: id - Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
arxiv:2601.18734· evidence: title - Reinforcement Learning via Self-Distillation
arxiv:2601.20802· evidence: title - Self-Improving Pretraining: using post-trained models to pretrain better models
arxiv:2601.21343· evidence: id - iGRPO: Self-Feedback-Driven LLM Reasoning
arxiv:2602.09000· evidence: title - Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
arxiv:2603.24472· evidence: title - Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes
arxiv:2603.25562· evidence: title - Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing
arxiv:2604.02288· evidence: id - Skip-Connected Policy Optimization for Implicit Advantage
arxiv:2604.08690· evidence: title - Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
arxiv:2604.13016· evidence: id - GRPO-VPS: Enhancing Group Relative Policy Optimization with Verifiable Process Supervision for Effective Reasoning
arxiv:2604.20659· evidence: id - Revisiting Reinforcement Learning with Verifiable Rewards from a Contrastive Perspective
arxiv:2605.12969· evidence: title - From Reasoning Chains to Verifiable Subproblems: Curriculum Reinforcement Learning Enables Credit Assignment for LLM Reasoning
arxiv:2605.22074· evidence: title - OPRD: On-Policy Representation Distillation
arxiv:2606.06021· evidence: title - Learning from Own Solutions: Self-Conditioned Credit Assignment for Reinforcement Learning with Verifiable Rewards
arxiv:2606.18810· evidence: title - Weight-Space Geometry of Offline Reasoning Training
arxiv:2606.23740· evidence: id - SPADE: Self-Play in Adaptive Synthetic Executable Environments
arxiv:2608.19197· evidence: id - TTPO: Test-Time Policy Optimization
arxiv:2608.27448· evidence: title - Recursive Self-Improvement via On-Policy Distillation for Reasoning
arxiv:2609.30652· evidence: title - RLTL;DR: Self-improvement by Internalizing Self-generated Feedback
arxiv:2609.37633· evidence: title - GRPO++: Tricks for Making RL Actually Work (Cameron Wolfe)
url:cameronrwolfe.substack.com/p/grpo-tricks· evidence: id