{"total":60,"rows":[{"id":"2601.05242","title":"GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization","created":"2026-01-08","cited_by_count":193,"area":"lr"},{"id":"2505.07686","title":"S-GRPO: Early Exit via Reinforcement Learning in Reasoning Models","created":"2025-05-12","cited_by_count":87,"area":"lr"},{"id":"2505.10832","title":"Learning When to Think: Shaping Adaptive Reasoning in R1-Style Models via Multi-Stage RL","created":"2025-05-16","cited_by_count":62,"area":"lr"},{"id":"2509.13769","title":"AdaThinkDrive: Adaptive Thinking via Reinforcement Learning for Autonomous Driving","created":"2025-09-17","cited_by_count":58,"area":"lr"},{"id":"2506.14755","title":"Optimizing Length Compression in Large Reasoning Models","created":"2025-06-17","cited_by_count":38,"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":"2508.13141","title":"OptimalThinkingBench: Evaluating Over and Underthinking in LLMs","created":"2025-08-18","cited_by_count":35,"area":"lr"},{"id":"2508.10293","title":"Promoting Efficient Reasoning with Verifiable Stepwise Reward","created":"2025-08-14","cited_by_count":28,"area":"lr"},{"id":"2505.18298","title":"Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards","created":"2025-05-23","cited_by_count":20,"area":"lr"},{"id":"2510.10409","title":"Trace Length is a Simple Uncertainty Signal in Reasoning Models","created":"2025-10-12","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":"2507.09662","title":"Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey","created":"2025-07-13","cited_by_count":18,"area":"lr"},{"id":"2506.02397","title":"OThink-R1: Intrinsic Fast/Slow Thinking Mode Switching for Over-Reasoning Mitigation","created":"2025-06-03","cited_by_count":17,"area":"lr"},{"id":"2510.04474","title":"DRPO: Efficient Reasoning via Decoupled Reward Policy Optimization","created":"2025-10-06","cited_by_count":16,"area":"lr"},{"id":"2510.14321","title":"Large Reasoning Embedding Models: Towards Next-Generation Dense Retrieval Paradigm","created":"2025-10-16","cited_by_count":9,"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":"2511.10714","title":"BadThink: Triggered Overthinking Attacks on Chain-of-Thought Reasoning in Large Language Models","created":"2025-11-13","cited_by_count":8,"area":"lr"},{"id":"2507.17307","title":"R-Stitch: Dynamic Trajectory Stitching for Efficient Reasoning","created":"2025-07-23","cited_by_count":7,"area":"lr"},{"id":"2510.05593","title":"Improving Chain-of-Thought Efficiency for Autoregressive Image Generation","created":"2025-10-07","cited_by_count":7,"area":"lr"},{"id":"2510.27419","title":"DeepCompress: A Dual Reward Strategy for Dynamically Exploring and Compressing Reasoning Chains","created":"2025-10-31","cited_by_count":7,"area":"lr"},{"id":"2601.08310","title":"ORBIT: On-policy Exploration-Exploitation for Controllable Multi-Budget Reasoning","created":"2026-01-13","cited_by_count":7,"area":"lr"},{"id":"2505.13326","title":"Thinking Short and Right Over Thinking Long: Serving LLM Reasoning Efficiently and Accurately","created":"2025-05-19","cited_by_count":6,"area":"lr"},{"id":"2505.19862","title":"REA-RL: Reflection-Aware Online Reinforcement Learning for Efficient Reasoning","created":"2025-05-26","cited_by_count":6,"area":"lr"},{"id":"2604.04930","title":"Early Stopping for Large Reasoning Models via Confidence Dynamics","created":"2026-04-06","cited_by_count":6,"area":"lr"},{"id":"2604.06787","title":"When Is Thinking Enough? Early Exit via Sufficiency Assessment for Efficient Reasoning","created":"2026-04-08","cited_by_count":6,"area":"lr"},{"id":"2510.03805","title":"Beyond Token Length: Step Pruner for Efficient and Accurate Reasoning in Large Language Models","created":"2025-10-04","cited_by_count":4,"area":"lr"},{"id":"2602.01472","title":"ConPress: Learning Efficient Reasoning from Multi-Question Contextual Pressure","created":"2026-02-01","cited_by_count":4,"area":"lr"},{"id":"2602.01982","title":"S3-CoT: Self-Sampled Succinct Reasoning Enables Efficient Chain-of-Thought LLMs","created":"2026-02-02","cited_by_count":4,"area":"lr"},{"id":"2603.08000","title":"SmartThinker: Progressive Chain-of-Thought Length Calibration for Efficient Large Language Model Reasoning","created":"2026-03-09","cited_by_count":4,"area":"lr"},{"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":"2510.10168","title":"Concise Reasoning in the Lens of Lagrangian Optimization","created":"2025-10-11","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":"2509.24560","title":"AdaThink-Med: Optimizing Inference-Time Compute for Medical Reasoning via Uncertainty Quantification","created":"2025-09-29","cited_by_count":2,"area":"lr"},{"id":"2510.10207","title":"Adaptive Dual Reasoner: Large Reasoning Models Can Think Efficiently by Hybrid Reasoning","created":"2025-10-11","cited_by_count":2,"area":"lr"},{"id":"2511.02690","title":"Curriculum Design for Trajectory-Constrained Agent: Compressing Chain-of-Thought Tokens in LLMs","created":"2025-11-04","cited_by_count":2,"area":"lr"},{"id":"2511.03408","title":"Efficient Reasoning via Thought-Training and Thought-Free Inference","created":"2025-11-05","cited_by_count":2,"area":"lr"},{"id":"2511.18864","title":"Think Before You Prune: Selective Self-Generated Calibration for Pruning Large Reasoning Models","created":"2025-11-24","cited_by_count":2,"area":"lr"},{"id":"2602.14917","title":"BFS-PO: Best-First Search for Large Reasoning Models","created":"2026-02-16","cited_by_count":2,"area":"lr"},{"id":"2603.17449","title":"TRiMS: Real-Time Tracking of Minimal Sufficient Length for Efficient Reasoning via RL","created":"2026-03-18","cited_by_count":2,"area":"lr"},{"id":"2511.22891","title":"ORION: Teaching Language Models to Reason Efficiently in the Language of Thought","created":"2025-11-28","cited_by_count":1,"area":"lr"},{"id":"2602.02909","title":"Reasoning about Reasoning: BAPO Bounds on Chain-of-Thought Token Complexity in LLMs","created":"2026-02-02","cited_by_count":1,"area":"lr"},{"id":"2603.19779","title":"One Model, Two Minds: Task-Conditioned Reasoning for Unified Image Quality and Aesthetic Assessment","created":"2026-03-20","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":"2605.12969","title":"Revisiting Reinforcement Learning with Verifiable Rewards from a Contrastive Perspective","created":"2026-05-13","cited_by_count":1,"area":"lr"},{"id":"2605.13165","title":"STOP: Structured On-Policy Pruning of Long-Form Reasoning in Low-Data Regimes","created":"2026-05-13","cited_by_count":1,"area":"lr"},{"id":"2606.03503","title":"ThoughtFold: Folding Reasoning Chains via Introspective Preference Learning","created":"2026-06-02","cited_by_count":1,"area":"lr"},{"id":"2607.09786","title":"Length Penalties Make Chain-of-Thought Less Monitorable","created":"2026-07-08","cited_by_count":1,"area":"lr"},{"id":"2602.00760","title":"APR: Penalizing Structural Redundancy in Large Reasoning Models via Anchor-based Process Rewards","created":"2026-01-31","cited_by_count":0,"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":"2602.22508","title":"Metacognitive Behavioral Tuning of Large Language Models for Multi-Hop Question Answering","created":"2026-02-26","cited_by_count":0,"area":"lr"},{"id":"2603.18533","title":"Balancing the Reasoning Load: Difficulty-Differentiated Policy Optimization with Length Redistribution for Efficient and Robust Reinforcement Learning","created":"2026-03-19","cited_by_count":0,"area":"lr"},{"id":"2604.02322","title":"Batched Contextual Reinforcement: A Task-Scaling Law for Efficient Reasoning","created":"2026-04-02","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":"2605.09806","title":"LEAD: Length-Efficient Adaptive and Dynamic Reasoning for Large Language Models","created":"2026-05-10","cited_by_count":0,"area":"lr"},{"id":"2605.22211","title":"CLORE: Content-Level Optimization for Reasoning Efficiency","created":"2026-05-21","cited_by_count":0,"area":"lr"},{"id":"2608.25583","title":"GRIP: Granular Reward-Guided Parameter Interpolation for Efficient Reasoning","created":"2026-08-26","cited_by_count":0,"area":"lr"},{"id":"2609.31619","title":"Learning to Stop without Learning to Stop: Self-Supervised Confidence Training Improves Reasoning Efficiency","created":"2026-09-25","cited_by_count":0,"area":"lr"},{"id":"2609.38854","title":"Mitigating the Length-Scaling Tax with Online Distillation","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.19890","title":"Frustratingly Easy Majority Voting Using Length Conditioning","created":"2026-10-14","cited_by_count":0,"area":"lr"}],"next_cursor":null}