{"total":175,"rows":[{"id":"2508.15260","title":"Deep Think with Confidence","created":"2025-08-21","cited_by_count":205,"area":"lr"},{"id":"2504.10903","title":"Efficient Reasoning Models: A Survey","created":"2025-04-15","cited_by_count":95,"area":"lr"},{"id":"2505.11896","title":"AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning","created":"2025-05-17","cited_by_count":87,"area":"lr"},{"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":"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":"2603.05433","title":"CRISP: Compressed Reasoning via Iterative Self-Policy Distillation","created":"2026-03-05","cited_by_count":58,"area":"lr"},{"id":"2506.04210","title":"Does Thinking More always Help? Mirage of Test-Time Scaling in Reasoning Models","created":"2025-06-04","cited_by_count":53,"area":"lr"},{"id":"2506.05256","title":"Just Enough Thinking: Efficient Reasoning with Adaptive Length Penalties Reinforcement Learning","created":"2025-06-05","cited_by_count":52,"area":"lr"},{"id":"2505.18822","title":"AdaCtrl: Towards Adaptive and Controllable Reasoning via Difficulty-Aware Budgeting","created":"2025-05-24","cited_by_count":50,"area":"lr"},{"id":"2506.02536","title":"Answer Convergence as a Signal for Early Stopping in Reasoning","created":"2025-06-03","cited_by_count":40,"area":"lr"},{"id":"2505.20258","title":"ARM: Adaptive Reasoning Model","created":"2025-05-26","cited_by_count":39,"area":"lr"},{"id":"2506.14755","title":"Optimizing Length Compression in Large Reasoning Models","created":"2025-06-17","cited_by_count":38,"area":"lr"},{"id":"2508.03346","title":"Making Slow Thinking Faster: Compressing LLM Chain-of-Thought via Step Entropy","created":"2025-08-05","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":"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":"2506.13752","title":"Steering LLM Thinking with Budget Guidance","created":"2025-06-16","cited_by_count":33,"area":"lr"},{"id":"2505.16838","title":"R1-Compress: Long Chain-of-Thought Compression via Chunk Compression and Search","created":"2025-05-22","cited_by_count":30,"area":"lr"},{"id":"2508.17196","title":"BudgetThinker: Empowering Budget-aware LLM Reasoning with Control Tokens","created":"2025-08-24","cited_by_count":29,"area":"lr"},{"id":"2505.23727","title":"PixelThink: Towards Efficient Chain-of-Pixel Reasoning","created":"2025-05-29","cited_by_count":28,"area":"lr"},{"id":"2508.10293","title":"Promoting Efficient Reasoning with Verifiable Stepwise Reward","created":"2025-08-14","cited_by_count":28,"area":"lr"},{"id":"2505.18086","title":"Stable Reinforcement Learning for Efficient Reasoning","created":"2025-05-23","cited_by_count":27,"area":"lr"},{"id":"2505.17941","title":"VeriThinker: Learning to Verify Makes Reasoning Model Efficient","created":"2025-05-23","cited_by_count":24,"area":"lr"},{"id":"2507.04742","title":"Activation Steering for Chain-of-Thought Compression","created":"2025-07-07","cited_by_count":24,"area":"lr"},{"id":"2505.24098","title":"HardTests: Synthesizing High-Quality Test Cases for LLM Coding","created":"2025-05-30","cited_by_count":23,"area":"lr"},{"id":"2505.16315","title":"Incentivizing Dual Process Thinking for Efficient Large Language Model Reasoning","created":"2025-05-22","cited_by_count":21,"area":"lr"},{"id":"2505.18404","title":"Thought calibration: Efficient and confident test-time scaling","created":"2025-05-23","cited_by_count":21,"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":"2505.11225","title":"HAPO: Training Language Models to Reason Concisely via History-Aware Policy Optimization","created":"2025-05-16","cited_by_count":19,"area":"lr"},{"id":"2505.16826","title":"KTAE: A Model-Free Algorithm to Key-Tokens Advantage Estimation in Mathematical Reasoning","created":"2025-05-22","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":"2604.09852","title":"MEMENTO: Teaching LLMs to Manage Their Own Context","created":"2026-04-10","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":"2505.11827","title":"Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning","created":"2025-05-17","cited_by_count":16,"area":"lr"},{"id":"2505.23653","title":"How do Transformers Learn Implicit Reasoning?","created":"2025-05-29","cited_by_count":16,"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":"2506.22058","title":"Lost at the Beginning of Reasoning","created":"2025-06-27","cited_by_count":15,"area":"lr"},{"id":"2505.07961","title":"Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement","created":"2025-05-12","cited_by_count":14,"area":"lr"},{"id":"2505.17155","title":"TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling","created":"2025-05-22","cited_by_count":14,"area":"lr"},{"id":"2505.17250","title":"ConciseRL: Conciseness-Guided Reinforcement Learning for Efficient Reasoning Models","created":"2025-05-22","cited_by_count":14,"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":"2510.06557","title":"The Markovian Thinker: Architecture-Agnostic Linear Scaling of Reasoning","created":"2025-10-08","cited_by_count":13,"area":"lr"},{"id":"2510.15211","title":"ReasonIF: Large Reasoning Models Fail to Follow Instructions During Reasoning","created":"2025-10-17","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":"2601.21919","title":"Self-Compression of Chain-of-Thought via Multi-Agent Reinforcement Learning","created":"2026-01-29","cited_by_count":13,"area":"lr"},{"id":"2505.14009","title":"Activation-Guided Consensus Merging for Large Language Models","created":"2025-05-20","cited_by_count":12,"area":"lr"},{"id":"2505.22662","title":"AutoL2S: Auto Long-Short Reasoning for Efficient Large Language Models","created":"2025-05-28","cited_by_count":12,"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":"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":"2505.21765","title":"Don't Think Longer, Think Wisely: Optimizing Thinking Dynamics for Large Reasoning Models","created":"2025-05-27","cited_by_count":11,"area":"lr"},{"id":"2507.15758","title":"LAPO: Internalizing Reasoning Efficiency via Length-Adaptive Policy Optimization","created":"2025-07-21","cited_by_count":11,"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":"2603.10887","title":"Dynamics-Predictive Sampling for Active RL Finetuning of Large Reasoning Models","created":"2026-03-11","cited_by_count":11,"area":"lr"},{"id":"2504.10368","title":"Exploring the System 1 Thinking Capability of Large Reasoning Models","created":"2025-04-14","cited_by_count":10,"area":"lr"},{"id":"2505.21097","title":"Thinker: Learning to Think Fast and Slow","created":"2025-05-27","cited_by_count":10,"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":"2510.08525","title":"Which Heads Matter for Reasoning? RL-Guided KV Cache Compression","created":"2025-10-09","cited_by_count":10,"area":"lr"},{"id":"2506.07104","title":"How Far Are We from Optimal Reasoning Efficiency?","created":"2025-06-08","cited_by_count":8,"area":"lr"},{"id":"2506.15647","title":"Exploring and Exploiting the Inherent Efficiency within Large Reasoning Models for Self-Guided Efficiency Enhancement","created":"2025-06-18","cited_by_count":8,"area":"lr"},{"id":"2507.15844","title":"Hierarchical Budget Policy Optimization for Adaptive Reasoning","created":"2025-07-21","cited_by_count":8,"area":"lr"},{"id":"2512.19995","title":"Schoenfeld's Anatomy of Mathematical Reasoning by Language Models","created":"2025-12-23","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":"2601.22069","title":"VTC-R1: Vision-Text Compression for Efficient Long-Context Reasoning","created":"2026-01-29","cited_by_count":8,"area":"lr"},{"id":"2603.07915","title":"Ares: Adaptive Reasoning Effort Selection for Efficient LLM Agents","created":"2026-03-09","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":"2510.27419","title":"DeepCompress: A Dual Reward Strategy for Dynamically Exploring and Compressing Reasoning Chains","created":"2025-10-31","cited_by_count":7,"area":"lr"},{"id":"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":"2509.25426","title":"RADAR: Reasoning-Ability and Difficulty-Aware Routing for Reasoning LLMs","created":"2025-09-29","cited_by_count":6,"area":"lr"},{"id":"2511.00640","title":"DTS: Enhancing Large Reasoning Models via Decoding Tree Sketching","created":"2025-11-01","cited_by_count":6,"area":"lr"},{"id":"2601.19952","title":"LTS-VoiceAgent: A Listen-Think-Speak Framework for Efficient Streaming Voice Interaction via Semantic Triggering and Incremental Reasoning","created":"2026-01-26","cited_by_count":6,"area":"lr"},{"id":"2506.11077","title":"CyclicReflex: Improving Reasoning Models via Cyclical Reflection Token Scheduling","created":"2025-06-04","cited_by_count":5,"area":"lr"},{"id":"2506.20241","title":"Enhancing Large Language Models through Structured Reasoning","created":"2025-06-25","cited_by_count":5,"area":"lr"},{"id":"2510.10013","title":"Path Drift in Large Reasoning Models:How First-Person Commitments Override Safety","created":"2025-10-11","cited_by_count":5,"area":"lr"},{"id":"2509.22034","title":"The Thinking Spectrum: An Empirical Study of Tunable Reasoning in LLMs through Model Merging","created":"2025-09-26","cited_by_count":4,"area":"lr"},{"id":"2509.23967","title":"HiPO: Hybrid Policy Optimization for Dynamic Reasoning in LLMs","created":"2025-09-28","cited_by_count":4,"area":"lr"},{"id":"2509.24711","title":"Stop Before You Fail: Operational Capability Boundaries for Mitigating Unproductive Reasoning in Large Reasoning Models","created":"2025-09-29","cited_by_count":4,"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":"2510.03805","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":"2510.08163","title":"ARM2: Adaptive Reasoning Model with Vision Understanding and Executable Code","created":"2025-10-09","cited_by_count":4,"area":"lr"},{"id":"2510.20909","title":"Code-enabled language models can outperform reasoning models on diverse tasks","created":"2025-10-23","cited_by_count":4,"area":"lr"},{"id":"2512.01925","title":"Rectifying LLM Thought from Lens of Optimization","created":"2025-12-01","cited_by_count":4,"area":"lr"},{"id":"2601.18146","title":"Think When Needed: Model-Aware Reasoning Routing for LLM-based Ranking","created":"2026-01-26","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":"2602.05539","title":"Steering Large Reasoning Models towards Concise Reasoning via Flow Matching","created":"2026-02-05","cited_by_count":4,"area":"lr"},{"id":"2602.13407","title":"On-Policy Supervised Fine-Tuning for Efficient Reasoning","created":"2026-02-13","cited_by_count":4,"area":"lr"},{"id":"2602.20945","title":"The Art of Efficient Reasoning: Data, Reward, and Optimization","created":"2026-02-24","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":"2604.01170","title":"Online Reasoning Calibration: Test-Time Training Enables Generalizable Conformal LLM Reasoning","created":"2026-04-01","cited_by_count":4,"area":"lr"},{"id":"2508.10164","title":"Pruning Long Chain-of-Thought of Large Reasoning Models via Small-Scale Preference Optimization","created":"2025-08-13","cited_by_count":3,"area":"lr"},{"id":"2509.23962","title":"Conditional Advantage Estimation for Reinforcement Learning in Large Reasoning Models","created":"2025-09-28","cited_by_count":3,"area":"lr"},{"id":"2509.25176","title":"SIRI: Scaling Iterative Reinforcement Learning with Interleaved Compression","created":"2025-09-29","cited_by_count":3,"area":"lr"},{"id":"2509.25958","title":"RoRecomp: Enhancing Reasoning Efficiency via Rollout Response Recomposition in Reinforcement Learning","created":"2025-09-30","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":"2510.12063","title":"ThinkPilot: Steering Reasoning Models via Automated Think-prefixes Optimization","created":"2025-10-14","cited_by_count":3,"area":"lr"},{"id":"2511.00536","title":"Word Salad Chopper: Reasoning Models Waste A Ton Of Decoding Budget On Useless Repetitions, Self-Knowingly","created":"2025-11-01","cited_by_count":3,"area":"lr"},{"id":"2511.11187","title":"ReTrace: Interactive Visualizations for Reasoning Traces of Large Reasoning Models","created":"2025-11-14","cited_by_count":3,"area":"lr"},{"id":"2601.06052","title":"Reinforcement Learning for Chain of Thought Compression with One-Domain-to-All Generalization","created":"2025-12-19","cited_by_count":3,"area":"lr"},{"id":"2602.10004","title":"ESTAR: Early-Stopping Token-Aware Reasoning For Efficient Inference","created":"2026-02-10","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"}],"next_cursor":"100"}