{"total":97,"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":"2507.14843","title":"The Invisible Leash: Why RLVR May or May Not Escape Its Origin","created":"2025-07-20","cited_by_count":97,"area":null},{"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":"2506.19767","title":"SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning","created":"2025-06-24","cited_by_count":84,"area":"lr"},{"id":"2507.01679","title":"Blending Supervised and Reinforcement Fine-Tuning with Prefix Sampling","created":"2025-07-02","cited_by_count":60,"area":"lr"},{"id":"2510.02245","title":"ExGRPO: Learning to Reason from Experience","created":"2025-10-02","cited_by_count":53,"area":"lr"},{"id":"2510.19807","title":"Scaf-GRPO: Scaffolded Group Relative Policy Optimization for Enhancing LLM Reasoning","created":"2025-10-22","cited_by_count":52,"area":"lr"},{"id":"2603.23871","title":"HDPO: Hybrid Distillation Policy Optimization via Privileged Self-Distillation","created":"2026-03-25","cited_by_count":42,"area":"lr"},{"id":"2508.00222","title":"RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization","created":"2025-07-31","cited_by_count":35,"area":"lr"},{"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":"2509.21128","title":"RL Squeezes, SFT Expands: A Comparative Study of Reasoning LLMs","created":"2025-09-25","cited_by_count":34,"area":"lr"},{"id":"2604.13010","title":"Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation","created":"2026-04-14","cited_by_count":33,"area":"lr"},{"id":"2509.18851","title":"NGRPO: Negative-enhanced Group Relative Policy Optimization","created":"2025-09-23","cited_by_count":32,"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":"2511.07332","title":"Grounding Computer Use Agents on Human Demonstrations","created":"2025-11-10","cited_by_count":22,"area":"agents"},{"id":"2509.03581","title":"Learning When to Plan: Efficiently Allocating Test-Time Compute for LLM Agents","created":"2025-09-03","cited_by_count":20,"area":"lr"},{"id":"2603.01063","title":"Unleashing VLA Potentials in Autonomous Driving via Explicit Learning from Failures","created":"2026-03-01","cited_by_count":19,"area":"vla"},{"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":"2510.04454","title":"Mitigating Forgetting Between Supervised and Reinforcement Learning Yields Stronger Reasoners","created":"2025-10-06","cited_by_count":16,"area":"lr"},{"id":"2509.14257","title":"Student-Centered Distillation Narrows the Agentic Gap Between Small and Large LLMs","created":"2025-09-12","cited_by_count":14,"area":"agents"},{"id":"2510.04028","title":"The Debate on RLVR Reasoning Capability Boundary: Shrinkage, Expansion, or Both? A Two-Stage Dynamic View","created":"2025-10-05","cited_by_count":13,"area":"lr"},{"id":"2512.21540","title":"Leash: Adaptive Length Penalty and Reward Shaping for Efficient Large Reasoning Model","created":"2025-12-25","cited_by_count":13,"area":"lr"},{"id":"2601.14249","title":"Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Alignment","created":"2026-01-20","cited_by_count":13,"area":"lr"},{"id":"2508.10026","title":"SABER: Switchable and Balanced Training for Efficient LLM Reasoning","created":"2025-08-08","cited_by_count":12,"area":"lr"},{"id":"2509.21882","title":"Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards","created":"2025-09-26","cited_by_count":12,"area":null},{"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":"2509.18849","title":"MAPO: Mixed Advantage Policy Optimization","created":"2025-09-23","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":"2507.13038","title":"MAD-Spear: A Conformity-Driven Prompt Injection Attack on Multi-Agent Debate Systems","created":"2025-07-17","cited_by_count":10,"area":"agents"},{"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":"2602.20722","title":"Buffer Matters: Unleashing the Power of Off-Policy Reinforcement Learning in Large Language Model Reasoning","created":"2026-02-24","cited_by_count":8,"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":"2602.05548","title":"Unveiling Implicit Advantage Symmetry: Why GRPO Struggles with Exploration and Difficulty Adaptation","created":"2026-02-05","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":"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":"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":"2602.18232","title":"Thinking by Subtraction: Confidence-Driven Contrastive Decoding for LLM Reasoning","created":"2026-02-20","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":"2508.06944","title":"AMFT: Aligning LLM Reasoners by Meta-Learning the Optimal Imitation-Exploration Balance","created":"2025-08-09","cited_by_count":5,"area":"lr"},{"id":"2607.28449","title":"Lightning OPD 2.0: Mitigating Style Bias in Cross-Teacher On-Policy Distillation for Large Reasoning Models","created":"2026-07-30","cited_by_count":5,"area":"lr"},{"id":"2508.06412","title":"Sample-efficient LLM Optimization with Reset Replay","created":"2025-08-08","cited_by_count":4,"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":"2511.19168","title":"RAVEN++: Pinpointing Fine-Grained Violations in Advertisement Videos with Active Reinforcement Reasoning","created":"2025-11-24","cited_by_count":4,"area":"lr"},{"id":"2603.01607","title":"CARE: Towards Clinical Accountability in Multi-Modal Medical Reasoning with an Evidence-Grounded Agentic Framework","created":"2026-03-02","cited_by_count":4,"area":"lr"},{"id":"2603.13842","title":"Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving","created":"2026-03-14","cited_by_count":4,"area":"driving"},{"id":"2604.04767","title":"Cog-DRIFT: Exploration on Adaptively Reformulated Instances Enables Learning from Hard Reasoning Problems","created":"2026-04-06","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":"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":"2510.26109","title":"Do Not Step Into the Same River Twice: Learning to Reason from Trial and Error","created":"2025-10-30","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":"2602.24110","title":"Recycling Failures: Salvaging Exploration in RLVR via Fine-Grained Off-Policy Guidance","created":"2026-02-27","cited_by_count":3,"area":"lr"},{"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":"2605.29563","title":"Planning with the Views","created":"2026-05-28","cited_by_count":3,"area":null},{"id":"2607.07674","title":"Max Out GRPO Signal: Adaptive Trace Prefix Control for Hard Reasoning Problems","created":"2026-07-08","cited_by_count":3,"area":null},{"id":"2511.04285","title":"RLoop: An Self-Improving Framework for Reinforcement Learning with Iterative Policy Initialization","created":"2025-11-06","cited_by_count":2,"area":"lr"},{"id":"2511.20814","title":"SPHINX: A Synthetic Environment for Visual Perception and Reasoning","created":"2025-11-25","cited_by_count":2,"area":"lr"},{"id":"2511.21056","title":"Bilevel Data Curation for LLM Fine-tuning: Offline Selection and Online Self-Refining Generation","created":"2025-11-26","cited_by_count":2,"area":null},{"id":"2601.09233","title":"GIFT: Reconciling Post-Training Objectives via Variational Finite-Temperature Gibbs Initialization","created":"2026-01-14","cited_by_count":2,"area":"lr"},{"id":"2509.18600","title":"OraPO: Oracle-educated Reinforcement Learning for Data-efficient and Factual Radiology Report Generation","created":"2025-09-23","cited_by_count":1,"area":null},{"id":"2510.06270","title":"MCCE: A Framework for Multi-LLM Collaborative Search in Discrete Spaces with Similarity-Filtered Preference Learning","created":"2025-10-06","cited_by_count":1,"area":null},{"id":"2512.04341","title":"Long-Horizon Model-Based Offline Reinforcement Learning Without Explicit Conservatism","created":"2025-12-04","cited_by_count":1,"area":"offlinerl"},{"id":"2602.00400","title":"KEPO: Knowledge-Enhanced Preference Optimization for Multimodal Reasoning with Applications to Medical VQA","created":"2026-01-30","cited_by_count":1,"area":"lr"},{"id":"2602.03022","title":"STAR: Similarity-guided Teacher-Assisted Refinement for Super-Tiny Function Calling Models","created":"2026-02-03","cited_by_count":1,"area":"agents"},{"id":"2602.20197","title":"Controllable Exploration in Hybrid-Policy RLVR for Multi-Modal Reasoning","created":"2026-02-22","cited_by_count":1,"area":"lr"},{"id":"2602.22225","title":"SmartChunk Retrieval: Query-Aware Chunk Compression with Planning for Efficient Document RAG","created":"2025-12-17","cited_by_count":1,"area":"rag"},{"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":"2604.16893","title":"EasyVideoR1: Easier RL for Video Understanding","created":"2026-04-18","cited_by_count":1,"area":"lr"},{"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":"2605.11505","title":"Selective Off-Policy Reference Tuning with Plan Guidance","created":"2026-05-12","cited_by_count":1,"area":"lr"},{"id":"2605.20075","title":"CopT: Contrastive On-Policy Thinking with Continuous Spaces for General and Agentic Reasoning","created":"2026-05-19","cited_by_count":1,"area":"lr"},{"id":"2605.25571","title":"AnE: Pushing the Reasoning Frontier of Multimodal LLMs via Anchor Evolution","created":"2026-05-25","cited_by_count":1,"area":"lr"},{"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":"2607.11506","title":"SCOPE-RL: Optimizing Reasoning Paths Before and After Success","created":"2026-07-13","cited_by_count":1,"area":"lr"},{"id":"2510.10606","title":"ViSurf: Visual Supervised-and-Reinforcement Fine-Tuning for Large Vision-and-Language Models","created":"2025-10-12","cited_by_count":0,"area":null},{"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":"2603.12875","title":"Test-time RL alignment exposes task familiarity artifacts in LLM benchmarks","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2604.15306","title":"Generalization in LLM Problem Solving: The Case of the Shortest Path","created":"2026-04-16","cited_by_count":0,"area":null},{"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":"2607.14895","title":"Leveraging Instruction Tuning and Merging for Reasoning Model Adaptation","created":"2026-07-16","cited_by_count":0,"area":"lr"},{"id":"2607.27787","title":"LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts","created":"2026-07-30","cited_by_count":0,"area":"lr"},{"id":"2608.14212","title":"APTER: Adaptive Post-Training with Expert-Grounded Rubrics","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2608.25243","title":"From Memorization to Absorption: Mixed-Policy RL for Continual Knowledge Injection","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.12419","title":"MInTRL: Off-policy Intervention can boost On-policy RL","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.20842","title":"COAL-SQL: Coverage-Guided Augmentation and Failure-Driven Learning for Text-to-SQL Post-Training","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2609.25618","title":"Reasoning-Preserving Fine-Tuning of Post-RL LLMs with Null-Basis LoRA","created":"2026-09-22","cited_by_count":0,"area":"lr"},{"id":"2610.04978","title":"What Will Post-Training Fix? Per-Problem Gains Are Shared Across Independent RL Runs, and Existing Checkpoints Predict Them Better Than A Priori Signals","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.18459","title":"Teacher-Guided Tool Learning for Small Language Models via Bidirectional KL Constraints","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}