{"total":87,"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":"2506.01347","title":"The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning","created":"2025-06-02","cited_by_count":162,"area":"lr"},{"id":"2507.10524","title":"Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation","created":"2025-07-14","cited_by_count":133,"area":null},{"id":"2604.03128","title":"Self-Distilled RLVR","created":"2026-04-03","cited_by_count":131,"area":"distill"},{"id":"2510.05381","title":"Context Length Alone Hurts LLM Performance Despite Perfect Retrieval","created":"2025-10-06","cited_by_count":127,"area":null},{"id":"2507.20673","title":"Geometric-Mean Policy Optimization","created":"2025-07-28","cited_by_count":111,"area":"lr"},{"id":"2507.07017","title":"First Return, Entropy-Eliciting Explore","created":"2025-07-09","cited_by_count":45,"area":"lr"},{"id":"2508.02120","title":"Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Models","created":"2025-08-04","cited_by_count":37,"area":"lr"},{"id":"2505.13975","title":"DRP: Distilled Reasoning Pruning with Skill-aware Step Decomposition for Efficient Large Reasoning Models","created":"2025-05-20","cited_by_count":30,"area":"lr"},{"id":"2512.09106","title":"Learning Unmasking Policies for Diffusion Language Models","created":"2025-12-09","cited_by_count":30,"area":"diffusion"},{"id":"2505.18086","title":"Stable Reinforcement Learning for Efficient Reasoning","created":"2025-05-23","cited_by_count":27,"area":"lr"},{"id":"2509.26522","title":"Entropy After </Think> for reasoning model early exiting","created":"2025-09-30","cited_by_count":24,"area":"lr"},{"id":"2511.06411","title":"SofT-GRPO: Surpassing Discrete-Token LLM Reinforcement Learning via Gumbel-Reparameterized Soft-Thinking Policy Optimization","created":"2025-11-09","cited_by_count":21,"area":"lr"},{"id":"2601.20614","title":"Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation","created":"2026-01-28","cited_by_count":19,"area":"lr"},{"id":"2602.08354","title":"Does Your Reasoning Model Implicitly Know When to Stop Thinking?","created":"2026-02-09","cited_by_count":19,"area":"lr"},{"id":"2508.17627","title":"The Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics Analysis","created":"2025-08-25","cited_by_count":18,"area":"lr"},{"id":"2605.28014","title":"ROSD: Reflective On-Policy Self-Distillation for Language Model Reasoning across Domains","created":"2026-05-27","cited_by_count":17,"area":"lr"},{"id":"2507.19672","title":"Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges","created":"2025-07-25","cited_by_count":15,"area":"alignment"},{"id":"2510.06557","title":"The Markovian Thinker: Architecture-Agnostic Linear Scaling of Reasoning","created":"2025-10-08","cited_by_count":13,"area":"lr"},{"id":"2601.21919","title":"Self-Compression of Chain-of-Thought via Multi-Agent Reinforcement Learning","created":"2026-01-29","cited_by_count":13,"area":"lr"},{"id":"2508.02511","title":"Test-time Prompt Intervention","created":"2025-08-04","cited_by_count":12,"area":"lr"},{"id":"2508.03100","title":"AVATAR: Reinforcement Learning to See, Hear, and Reason Over Video","created":"2025-08-05","cited_by_count":12,"area":"lr"},{"id":"2602.17025","title":"WS-GRPO: Weakly-Supervised Group-Relative Policy Optimization for Rollout-Efficient Reasoning","created":"2026-02-19","cited_by_count":12,"area":"lr"},{"id":"2508.02833","title":"TIC-GRPO: Provable and Efficient Optimization for Reinforcement Learning from Human Feedback","created":"2025-08-04","cited_by_count":11,"area":"lr"},{"id":"2508.18773","title":"ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Models","created":"2025-08-26","cited_by_count":11,"area":"lr"},{"id":"2509.18849","title":"MAPO: Mixed Advantage Policy Optimization","created":"2025-09-23","cited_by_count":11,"area":"lr"},{"id":"2509.23392","title":"Your Models Have Thought Enough: Training Large Reasoning Models to Stop Overthinking","created":"2025-09-27","cited_by_count":10,"area":"lr"},{"id":"2512.24574","title":"Understanding and Steering the Cognitive Behaviors of Reasoning Models at Test-Time","created":"2025-12-31","cited_by_count":10,"area":"lr"},{"id":"2603.24840","title":"Prune as You Generate: Online Rollout Pruning for Faster and Better RLVR","created":"2026-03-25","cited_by_count":10,"area":"lr"},{"id":"2606.05152","title":"Reinforcement Learning from Rich Feedback with Distributional DAgger","created":"2026-06-03","cited_by_count":10,"area":"lr"},{"id":"2602.09953","title":"ATTNPO: Attention-Guided Process Supervision for Efficient Reasoning","created":"2026-02-10","cited_by_count":9,"area":"lr"},{"id":"2605.02913","title":"Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning","created":"2026-04-08","cited_by_count":9,"area":"lr"},{"id":"2509.25160","title":"GSM8K-V: Can Vision Language Models Solve Grade School Math Word Problems in Visual Contexts","created":"2025-09-29","cited_by_count":8,"area":"lr"},{"id":"2601.05053","title":"Reinforced Efficient Reasoning via Semantically Diverse Exploration","created":"2026-01-08","cited_by_count":8,"area":"lr"},{"id":"2601.11340","title":"Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language Models","created":"2026-01-16","cited_by_count":8,"area":"lr"},{"id":"2604.02967","title":"FoE: Forest of Errors Makes the First Solution the Best in Large Reasoning Models","created":"2026-04-03","cited_by_count":8,"area":"lr"},{"id":"2606.04036","title":"Self-Distilled Policy Gradient","created":"2026-06-02","cited_by_count":8,"area":"lr"},{"id":"2509.08814","title":"Merge-of-Thought Distillation","created":"2025-09-10","cited_by_count":7,"area":"lr"},{"id":"2510.08026","title":"PEAR: Phase Entropy Aware Reward for Efficient Reasoning","created":"2025-10-09","cited_by_count":5,"area":"lr"},{"id":"2603.10101","title":"CLIPO: Contrastive Learning in Policy Optimization Generalizes RLVR","created":"2026-03-10","cited_by_count":5,"area":"lr"},{"id":"2604.20659","title":"GRPO-VPS: Enhancing Group Relative Policy Optimization with Verifiable Process Supervision for Effective Reasoning","created":"2026-04-22","cited_by_count":5,"area":"lr"},{"id":"2604.27083","title":"Co-Evolving Policy Distillation","created":"2026-04-29","cited_by_count":5,"area":null},{"id":"2507.22037","title":"Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security","created":"2025-07-29","cited_by_count":4,"area":"mllm"},{"id":"2509.25827","title":"Overthinking Reduction with Decoupled Rewards and Curriculum Data Scheduling","created":"2025-09-30","cited_by_count":4,"area":"lr"},{"id":"2602.05539","title":"Steering Large Reasoning Models towards Concise Reasoning via Flow Matching","created":"2026-02-05","cited_by_count":4,"area":"lr"},{"id":"2508.17637","title":"Weights-Rotated Preference Optimization for Large Language Models","created":"2025-08-25","cited_by_count":3,"area":"alignment"},{"id":"2508.17803","title":"DRQA: Dynamic Reasoning Quota Allocation for Controlling Overthinking in Reasoning Large Language Models","created":"2025-08-25","cited_by_count":3,"area":"lr"},{"id":"2510.03259","title":"Verifying Meta-Awareness via Predictive Rewards in Reasoning Models","created":"2025-09-26","cited_by_count":3,"area":"lr"},{"id":"2510.23486","title":"Learning to Reason Efficiently with Discounted Reinforcement Learning","created":"2025-10-27","cited_by_count":3,"area":"lr"},{"id":"2511.16331","title":"Incorporating Self-Rewriting into Large Language Model Reasoning Reinforcement","created":"2025-11-20","cited_by_count":3,"area":"lr"},{"id":"2601.21414","title":"System 1&2 Synergy via Dynamic Model Interpolation","created":"2026-01-29","cited_by_count":3,"area":null},{"id":"2602.10004","title":"ESTAR: Early-Stopping Token-Aware Reasoning For Efficient Inference","created":"2026-02-10","cited_by_count":3,"area":"lr"},{"id":"2602.19049","title":"IAPO: Information-Aware Policy Optimization for Token-Efficient Reasoning","created":"2026-02-22","cited_by_count":3,"area":"lr"},{"id":"2605.24998","title":"Better, Faster: Harnessing Self-Improvement in Large Reasoning Models","created":"2026-05-24","cited_by_count":3,"area":"lr"},{"id":"2508.18651","title":"Breaking the Trade-Off Between Faithfulness and Expressiveness for Large Language Models","created":"2025-08-26","cited_by_count":2,"area":null},{"id":"2511.06380","title":"What Makes Reasoning Invalid: Echo Reflection Mitigation for Large Language Models","created":"2025-11-09","cited_by_count":2,"area":"lr"},{"id":"2511.09780","title":"Hail to the Thief: Exploring Attacks and Defenses in Decentralised GRPO","created":"2025-11-12","cited_by_count":2,"area":"lr"},{"id":"2605.11467","title":"Drop the Act: Probe-Filtered RL for Faithful Chain-of-Thought Reasoning","created":"2026-05-12","cited_by_count":2,"area":"lr"},{"id":"2605.27965","title":"The Shape of Overthinking: Backtracking Bursts in Long Reasoning Traces","created":"2026-05-27","cited_by_count":2,"area":"lr"},{"id":"2608.26070","title":"Prefix Sliding for efficient test-time scaling","created":"2026-08-26","cited_by_count":2,"area":"lr"},{"id":"2509.24957","title":"Intra-request branch orchestration for efficient LLM reasoning","created":"2025-09-29","cited_by_count":1,"area":"lr"},{"id":"2601.04954","title":"Precision over Diversity: High-Precision Reward Generalizes to Robust Instruction Following","created":"2026-01-08","cited_by_count":1,"area":null},{"id":"2601.22521","title":"One Ring to Rule Them All: Unifying Group-Based RL via Dynamic Power-Mean Geometry","created":"2026-01-30","cited_by_count":1,"area":"lr"},{"id":"2602.01198","title":"A State-Transition Framework for Efficient LLM Reasoning","created":"2026-02-01","cited_by_count":1,"area":"lr"},{"id":"2602.20759","title":"Overton Pluralistic Reinforcement Learning for Large Language Models","created":"2026-02-24","cited_by_count":1,"area":null},{"id":"2603.02266","title":"When Scaling Fails: Mitigating Audio Perception Decay of LALMs via Multi-Step Perception-Aware Reasoning","created":"2026-02-28","cited_by_count":1,"area":"lr"},{"id":"2603.18756","title":"Are complicated loss functions necessary for teaching LLMs to reason?","created":"2026-03-19","cited_by_count":1,"area":"lr"},{"id":"2604.06636","title":"SHAPE: Stage-aware Hierarchical Advantage via Potential Estimation for LLM Reasoning","created":"2026-04-08","cited_by_count":1,"area":"lr"},{"id":"2604.16890","title":"Step-GRPO: Internalizing Dynamic Early Exit for Efficient Reasoning","created":"2026-04-18","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":"2605.07316","title":"Implicit Compression Regularization: Concise Reasoning via Internal Shorter Distributions in RL Post-Training","created":"2026-05-08","cited_by_count":1,"area":"lr"},{"id":"2605.11505","title":"Selective Off-Policy Reference Tuning with Plan Guidance","created":"2026-05-12","cited_by_count":1,"area":"lr"},{"id":"2606.03087","title":"Learning to Solve, Forgetting to Retain: Correct-Set Turnover in RLVR","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.03503","title":"ThoughtFold: Folding Reasoning Chains via Introspective Preference Learning","created":"2026-06-02","cited_by_count":1,"area":"lr"},{"id":"2606.08684","title":"BLUE: Toward Better Language Use in Efficient Vision-Language-Action Models for Autonomous Driving","created":"2026-06-07","cited_by_count":1,"area":"vla"},{"id":"2607.19345","title":"Copy Less, Ground More: Overcoming Repetitive Copying in Long-Context Reasoning via Evidence-Aware Reinforcement Learning","created":"2026-07-21","cited_by_count":1,"area":"lr"},{"id":"2602.12526","title":"Constraint-Rectified Training for Efficient Chain-of-Thought","created":"2026-02-13","cited_by_count":0,"area":"lr"},{"id":"2604.05643","title":"Graph-Based Chain-of-Thought Pruning for Reducing Redundant Reflections in Reasoning LLMs","created":"2026-04-07","cited_by_count":0,"area":"lr"},{"id":"2604.11510","title":"Policy Split: Incentivizing Dual-Mode Exploration in LLM Reinforcement with Dual-Mode Entropy Regularization","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2604.17312","title":"A Survey of Reinforcement Learning for Large Language Models under Data Scarcity: Challenges and Solutions","created":"2026-04-19","cited_by_count":0,"area":"lr"},{"id":"2605.00323","title":"Online Self-Calibration Against Hallucination in Vision-Language Models","created":"2026-05-01","cited_by_count":0,"area":"mllm"},{"id":"2605.14062","title":"Know When To Fold 'Em: Token-Efficient LLM Synthetic Data Generation via Multi-Stage In-Flight Rejection","created":"2026-05-13","cited_by_count":0,"area":"synth"},{"id":"2606.07520","title":"TinyJudge: Unverifiable Constraint Alignment via Lightweight Specialist Ensembles","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2606.08875","title":"Can the Environment Speak for Itself? $T^{2}$-GRPO: A Turn-Trajectory Group Relative Policy Optimization for Caregiver Agents","created":"2026-06-07","cited_by_count":0,"area":"lr"},{"id":"2607.21793","title":"QLPO: Quadrant-weighted Sampling for Length-aware Policy Optimization","created":"2026-07-23","cited_by_count":0,"area":"lr"},{"id":"2607.28166","title":"Commit Locally, Exit Globally: Coordinating Adaptive Sampling and Early Exit in Diffusion Language Models","created":"2026-07-30","cited_by_count":0,"area":"diffusion"},{"id":"2609.38817","title":"When Reasoning Goes Astray: Attention Dynamics of Uncontrolled Reasoning","created":"2026-09-30","cited_by_count":0,"area":"lr"}],"next_cursor":null}