{"total":36,"rows":[{"id":"2508.09726","title":"Sample More to Think Less: Group Filtered Policy Optimization for Concise Reasoning","created":"2025-08-13","cited_by_count":75,"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":"2510.15110","title":"DLER: Doing Length pEnalty Right - Incentivizing More Intelligence per Token via Reinforcement Learning","created":"2025-10-16","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":"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":"2508.02178","title":"Reconsidering Overthinking: Penalizing Internal and External Redundancy in CoT Reasoning","created":"2025-08-04","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":"2510.19669","title":"DiffAdapt: Difficulty-Adaptive Reasoning for Token-Efficient LLM Inference","created":"2025-10-22","cited_by_count":11,"area":"lr"},{"id":"2601.03823","title":"Step Potential Advantage Estimation: Harnessing Intermediate Confidence and Correctness for Efficient Mathematical Reasoning","created":"2026-01-07","cited_by_count":9,"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":"2602.09305","title":"Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation","created":"2026-02-10","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":"2509.25827","title":"Overthinking Reduction with Decoupled Rewards and Curriculum Data Scheduling","created":"2025-09-30","cited_by_count":4,"area":"lr"},{"id":"2510.15374","title":"Towards Flash Thinking via Decoupled Advantage Policy Optimization","created":"2025-10-17","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":"2511.14258","title":"Entropy-Guided Reasoning Compression","created":"2025-11-18","cited_by_count":3,"area":"lr"},{"id":"2603.00296","title":"Stepwise Penalization for Length-Efficient Chain-of-Thought Reasoning","created":"2026-02-27","cited_by_count":3,"area":"lr"},{"id":"2603.00578","title":"Draft-Thinking: Learning Efficient Reasoning in Long Chain-of-Thought LLMs","created":"2026-02-28","cited_by_count":3,"area":"lr"},{"id":"2603.07078","title":"CoTJudger: A Graph-Driven Framework for Automatic Evaluation of Chain-of-Thought Efficiency and Redundancy in LRMs","created":"2026-03-07","cited_by_count":3,"area":"lr"},{"id":"2510.01581","title":"Think Right: Learning to Mitigate Under-Over Thinking via Adaptive, Attentive Compression","created":"2025-10-02","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":"2511.09158","title":"Efficient Reasoning via Reward Model","created":"2025-11-12","cited_by_count":2,"area":"lr"},{"id":"2601.03969","title":"Anti-Length Shift: Dynamic Outlier Truncation for Training Efficient Reasoning Models","created":"2026-01-07","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":"2605.07501","title":"ExpThink: Experience-Guided Reinforcement Learning for Adaptive Chain-of-Thought Compression","created":"2026-05-08","cited_by_count":2,"area":"lr"},{"id":"2601.03506","title":"QA-Merging: Query-Adaptive Reasoning via Layer Selective Model Merging","created":"2026-01-07","cited_by_count":1,"area":"lr"},{"id":"2603.08462","title":"Reasoning as Compression: Unifying Budget Forcing via the Conditional Information Bottleneck","created":"2026-03-09","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":"2605.30832","title":"SLAT: Segment-Level Adaptive Trimming for Efficient CoT Reasoning","created":"2026-05-29","cited_by_count":1,"area":"lr"},{"id":"2606.02871","title":"Adaptive Latent Agentic Reasoning","created":"2026-06-01","cited_by_count":1,"area":"lr"},{"id":"2607.19962","title":"EvoThink: Evolving Thinking in Large Reasoning Models via Self-Pruning and Aha-Moment Preference Optimization","created":"2026-07-22","cited_by_count":1,"area":"lr"},{"id":"2601.07123","title":"ENTRA: Entropy-Based Redundancy Avoidance in Large Language Model Reasoning","created":"2026-01-12","cited_by_count":0,"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":"2609.17019","title":"SKIP: a Self-knowledge-guided Step-wise Preference Learning Framework for Concise Reasoning","created":"2026-09-15","cited_by_count":0,"area":"lr"}],"next_cursor":null}