{"total":84,"rows":[{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2508.11408","title":"On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting","created":"2025-08-15","cited_by_count":91,"area":"lr"},{"id":"2508.13755","title":"Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration","created":"2025-08-19","cited_by_count":43,"area":"lr"},{"id":"2509.04419","title":"Towards a Unified View of Large Language Model Post-Training","created":"2025-09-04","cited_by_count":36,"area":null},{"id":"2605.06387","title":"Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level","created":"2026-05-07","cited_by_count":35,"area":"lr"},{"id":"2509.12235","title":"RL Fine-Tuning Heals OOD Forgetting in SFT","created":"2025-09-08","cited_by_count":31,"area":"lr"},{"id":"2509.06948","title":"Beyond Two-Stage Training: Cooperative SFT and RL for LLM Reasoning","created":"2025-09-08","cited_by_count":30,"area":"lr"},{"id":"2509.25666","title":"Nudging the Boundaries of LLM Reasoning","created":"2025-09-30","cited_by_count":26,"area":"lr"},{"id":"2508.16546","title":"RL Is Neither a Panacea Nor a Mirage: Understanding Supervised vs. Reinforcement Learning Fine-Tuning for LLMs","created":"2025-08-22","cited_by_count":17,"area":null},{"id":"2602.01601","title":"Adaptive Rollout Allocation for Online Reinforcement Learning with Verifiable Rewards","created":"2026-02-02","cited_by_count":17,"area":null},{"id":"2510.04454","title":"Mitigating Forgetting Between Supervised and Reinforcement Learning Yields Stronger Reasoners","created":"2025-10-06","cited_by_count":16,"area":"lr"},{"id":"2509.24088","title":"CORRECT: COndensed eRror RECognition via knowledge Transfer in multi-agent systems","created":"2025-09-28","cited_by_count":15,"area":"agents"},{"id":"2510.09388","title":"Don't Tell the Answer, Truly Guide the Reasoning During RL Rollouts","created":"2025-10-10","cited_by_count":14,"area":"lr"},{"id":"2512.13095","title":"ADHint: Adaptive Hints with Difficulty Priors for Reinforcement Learning","created":"2025-12-15","cited_by_count":12,"area":"lr"},{"id":"2603.01223","title":"Learn Hard Problems During RL with Reference Guided Fine-tuning","created":"2026-03-01","cited_by_count":12,"area":"lr"},{"id":"2508.09883","title":"Beyond Scaling Law: A Data-Efficient Distillation Framework for Reasoning","created":"2025-08-13","cited_by_count":11,"area":"lr"},{"id":"2609.04108","title":"Sequential Beats Joint: On the Interplay between On-Policy Distillation and RLVR","created":"2026-09-03","cited_by_count":11,"area":"lr"},{"id":"2510.25510","title":"MTIR-SQL: Multi-turn Tool-Integrated Reasoning Reinforcement Learning for Text-to-SQL","created":"2025-10-29","cited_by_count":10,"area":"lr"},{"id":"2605.12652","title":"Multi-Rollout On-Policy Distillation via Peer Successes and Failures","created":"2026-05-12","cited_by_count":10,"area":"distill"},{"id":"2509.21854","title":"Perception-Consistency Multimodal Large Language Models Reasoning via Caption-Regularized Policy Optimization","created":"2025-09-26","cited_by_count":9,"area":"lr"},{"id":"2602.02244","title":"Entropy-Preserving Supervised Fine-Tuning via Adaptive Self-Distillation for Large Reasoning Models","created":"2026-02-02","cited_by_count":9,"area":"lr"},{"id":"2604.23747","title":"SFT-then-RL Outperforms Mixed-Policy Methods for LLM Reasoning","created":"2026-04-26","cited_by_count":9,"area":"lr"},{"id":"2508.07809","title":"EvoCoT: Overcoming the Exploration Bottleneck in Reinforcement Learning","created":"2025-08-11","cited_by_count":7,"area":"lr"},{"id":"2512.19126","title":"AWPO: Enhancing Tool-Use of Large Language Models through Adaptive Integration of Reasoning Rewards","created":"2025-12-22","cited_by_count":7,"area":"lr"},{"id":"2602.14147","title":"LaViDa-R1: Advancing Reasoning for Unified Multimodal Diffusion Language Models","created":"2026-02-15","cited_by_count":7,"area":"lr"},{"id":"2602.22732","title":"Generative Recommendation for Large-Scale Advertising","created":"2026-02-26","cited_by_count":7,"area":null},{"id":"2604.14054","title":"$\\pi$-Play: Multi-Agent Self-Play via Privileged Self-Distillation without External Data","created":"2026-04-15","cited_by_count":7,"area":"distill"},{"id":"2606.26027","title":"Why Multi-Step Tool-Use Reinforcement Learning Collapses and How Supervisory Signals Fix It","created":"2026-06-24","cited_by_count":7,"area":"agents"},{"id":"2508.03178","title":"Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following","created":"2025-08-05","cited_by_count":6,"area":"lr"},{"id":"2601.19928","title":"Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and Failures","created":"2026-01-11","cited_by_count":6,"area":"lr"},{"id":"2604.07941","title":"Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning","created":"2026-04-09","cited_by_count":6,"area":null},{"id":"2510.21978","title":"Beyond Reasoning Gains: Mitigating General-Capability Forgetting in Large Reasoning Models","created":"2025-10-24","cited_by_count":5,"area":"lr"},{"id":"2511.12429","title":"Tailored Primitive Initialization is the Secret Key to Reinforcement Learning","created":"2025-11-16","cited_by_count":4,"area":"lr"},{"id":"2605.12004","title":"Learning Agentic Policy from Action Guidance","created":"2026-05-12","cited_by_count":4,"area":"agents"},{"id":"2605.31228","title":"EchoRL: Reinforcement Learning via Rollout Echoing","created":"2026-05-29","cited_by_count":4,"area":"lr"},{"id":"2606.09932","title":"When RL Fails after SFT: Rejuvenating Model Plasticity for Robust SFT-to-RL Handoff","created":"2026-06-07","cited_by_count":4,"area":null},{"id":"2507.20252","title":"Post-Completion Learning for Language Models","created":"2025-07-27","cited_by_count":3,"area":null},{"id":"2508.16677","title":"Recall-Extend Dynamics: Enhancing Small Language Models through Controlled Exploration and Refined Offline Integration","created":"2025-08-21","cited_by_count":3,"area":"lr"},{"id":"2510.02227","title":"More Than One Teacher: Adaptive Multi-Guidance Policy Optimization for Diverse Exploration","created":"2025-10-02","cited_by_count":3,"area":"lr"},{"id":"2510.26519","title":"Think Outside the Policy: In-Context Steered Policy Optimization","created":"2025-10-30","cited_by_count":3,"area":"lr"},{"id":"2512.17636","title":"Trust-Region Adaptive Policy Optimization","created":"2025-12-19","cited_by_count":3,"area":"lr"},{"id":"2601.19916","title":"PaperAudit-Bench: Benchmarking Error Detection in Research Papers for Critical Automated Peer Review","created":"2026-01-07","cited_by_count":3,"area":null},{"id":"2603.13985","title":"Supervised Fine-Tuning versus Reinforcement Learning: A Study of Post-Training Methods for Large Language Models","created":"2026-03-14","cited_by_count":3,"area":null},{"id":"2604.14932","title":"WavAlign: Enhancing Intelligence and Expressiveness in Spoken Dialogue Models via Adaptive Hybrid Post-Training","created":"2026-04-16","cited_by_count":3,"area":null},{"id":"2604.20733","title":"Learning from the Near Future: Temporal Self-Distillation for RLVR","created":"2026-04-22","cited_by_count":3,"area":"distill"},{"id":"2607.01191","title":"Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning","created":"2026-07-01","cited_by_count":3,"area":"lr"},{"id":"2510.12643","title":"Reasoning Pattern Matters: Learning to Reason without Human Rationales","created":"2025-10-14","cited_by_count":2,"area":"lr"},{"id":"2511.01450","title":"Reg-DPO: SFT-Regularized Direct Preference Optimization with GT-Pair for Improving Video Generation","created":"2025-11-03","cited_by_count":2,"area":"alignment"},{"id":"2512.11470","title":"Rethinking Expert Trajectory Utilization in LLM Post-training for Mathematical Reasoning","created":"2025-12-12","cited_by_count":2,"area":"lr"},{"id":"2602.10815","title":"Why Does RL Generalize Better Than SFT? A Data-Centric Perspective on VLM Post-Training","created":"2026-02-11","cited_by_count":2,"area":"mllm"},{"id":"2605.22074","title":"From Reasoning Chains to Verifiable Subproblems: Curriculum Reinforcement Learning Enables Credit Assignment for LLM Reasoning","created":"2026-05-21","cited_by_count":2,"area":"lr"},{"id":"2606.08543","title":"PAEC: Position-Aware Entropy Calibration for LLM Reasoning in RLVR","created":"2026-06-07","cited_by_count":2,"area":"lr"},{"id":"2608.03573","title":"SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs","created":"2026-08-04","cited_by_count":2,"area":"lr"},{"id":"2608.25756","title":"TailSFT: Filtered Fine-Tuning Improves Post-Training Performance","created":"2026-08-26","cited_by_count":2,"area":"agents"},{"id":"2509.25148","title":"AAPA: Adversarially Anchored Preference Alignment for Post-Training of Large Language Models","created":"2025-09-29","cited_by_count":1,"area":"alignment"},{"id":"2510.14828","title":"RoboGPT-R1: Enhancing Robot Task Planning with Reinforcement Learning","created":"2025-10-16","cited_by_count":1,"area":"lr"},{"id":"2512.11277","title":"When Actions Teach You to Think: Reasoning-Action Synergy via Reinforcement Learning in Conversational Agents","created":"2025-12-12","cited_by_count":1,"area":"lr"},{"id":"2601.06498","title":"Spec-o3: A Tool-Augmented Vision-Language Agent for Rare Celestial Object Candidate Vetting via Automated Spectral Inspection","created":"2026-01-10","cited_by_count":1,"area":"agents"},{"id":"2602.10224","title":"Internalizing Meta-Experience into Memory for Guided Reinforcement Learning in Large Language Models","created":"2026-02-10","cited_by_count":1,"area":"lr"},{"id":"2604.08926","title":"Bridging SFT and RL: Dynamic Policy Optimization for Robust Reasoning","created":"2026-04-10","cited_by_count":1,"area":"lr"},{"id":"2604.14258","title":"GFT: From Imitation to Reward Fine-Tuning with Unbiased Group Advantages and Dynamic Coefficient Rectification","created":"2026-04-15","cited_by_count":1,"area":null},{"id":"2604.17337","title":"AutoSearch: Adaptive Search Depth for Efficient Agentic RAG via Reinforcement Learning","created":"2026-04-19","cited_by_count":1,"area":"rag"},{"id":"2605.00610","title":"Decouple before Integration: Test-time Synthesis of SFT and RLVR Task Vectors","created":"2026-05-01","cited_by_count":1,"area":null},{"id":"2605.05112","title":"Rollout Pass-Rate Control: Steering Binary-Reward RL Toward Its Most Informative Regime","created":"2026-05-06","cited_by_count":1,"area":"agents"},{"id":"2605.26184","title":"GAC: Noise-Aware Adaptive Mixing for Hybrid SFT-RL Post-Training","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2605.29303","title":"Entropy-KL Divergence-based Token Masking: A Novel Approach for Selective Fine-tuning of Large Language Models","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.04272","title":"RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.24064","title":"Beyond Trajectory Imitation: Strategy-Guided Policy Optimization for LLM Reasoning","created":"2026-06-23","cited_by_count":1,"area":"lr"},{"id":"2608.01755","title":"Deferred Exposure of Future Trajectories for Verifiable Reasoning in Autonomous Driving VLMs","created":"2026-08-03","cited_by_count":1,"area":"lr"},{"id":"2510.10201","title":"RLFR: Extending Reinforcement Learning for LLMs with Flow Environment","created":"2025-10-11","cited_by_count":0,"area":"lr"},{"id":"2602.01227","title":"Supervised Fine-Tuning Needs to Unlock the Potential of Token Priority","created":"2026-02-01","cited_by_count":0,"area":null},{"id":"2602.10819","title":"RePO: Bridging On-Policy Learning and Off-Policy Knowledge through Rephrasing Policy Optimization","created":"2026-02-11","cited_by_count":0,"area":"alignment"},{"id":"2603.11321","title":"Hindsight-Anchored Policy Optimization: Learning Through Hindsight with Thompson Sampling-Inspired Adaptive Gating","created":"2026-03-11","cited_by_count":0,"area":"lr"},{"id":"2603.18088","title":"Enhancing Reinforcement Learning Fine-Tuning with an Online Refiner","created":"2026-03-18","cited_by_count":0,"area":"lr"},{"id":"2604.05779","title":"What Models Know, How Well They Know It: Knowledge-Weighted Fine-Tuning for Learning When to Say \"I Don't Know\"","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2604.13175","title":"Pareto-Optimal Offline Reinforcement Learning via Smooth Tchebycheff Scalarization","created":"2026-04-14","cited_by_count":0,"area":"offlinerl"},{"id":"2605.08401","title":"AIPO: Learning to Reason from Active Interaction","created":"2026-05-08","cited_by_count":0,"area":"lr"},{"id":"2605.15012","title":"Boosting Reinforcement Learning with Verifiable Rewards via Randomly Selected Few-Shot Guidance","created":"2026-05-14","cited_by_count":0,"area":"lr"},{"id":"2606.22570","title":"What are Key Factors for Updates in RL for LLM Reasoning?","created":"2026-06-21","cited_by_count":0,"area":"lr"},{"id":"2609.28570","title":"DEEPO: Dual-Entropy Enhanced Policy Optimization for Hallucination in MLLMs","created":"2026-09-23","cited_by_count":0,"area":"lr"},{"id":"2610.03176","title":"Hindsight-Guided Rationale Distillation for Rare Disease Diagnosis","created":"2026-10-02","cited_by_count":0,"area":"lr"},{"id":"2610.05966","title":"HuatuoGPT-3: RL-Only Domain Adaptation from Base Models","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.12914","title":"OGPO: Offline Goal-conditioned Policy Optimization for Recoverable Vision-Language-Action Models","created":"2026-10-09","cited_by_count":0,"area":"vla"},{"id":"2610.17726","title":"TSRL: Trigger-based Supervised Reinforcement Learning for Continual Agent Training","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}