{"total":187,"rows":[{"id":"2506.06941","title":"The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity","created":"2025-06-07","cited_by_count":302,"area":"lr"},{"id":"2506.13757","title":"AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning","created":"2025-06-16","cited_by_count":260,"area":"lr"},{"id":"2504.15895","title":"Dynamic Early Exit in Reasoning Models","created":"2025-04-22","cited_by_count":219,"area":"lr"},{"id":"2505.19590","title":"Learning to Reason without External Rewards","created":"2025-05-26","cited_by_count":210,"area":"lr"},{"id":"2505.13417","title":"AdaptThink: Reasoning Models Can Learn When to Think","created":"2025-05-19","cited_by_count":147,"area":"lr"},{"id":"2505.00127","title":"Between Underthinking and Overthinking: An Empirical Study of Reasoning Length and correctness in LLMs","created":"2025-04-30","cited_by_count":117,"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":"2505.11896","title":"AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning","created":"2025-05-17","cited_by_count":87,"area":"lr"},{"id":"2506.08343","title":"Wait, We Don't Need to \"Wait\"! Removing Thinking Tokens Improves Reasoning Efficiency","created":"2025-06-10","cited_by_count":66,"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":"2505.24133","title":"R-KV: Redundancy-aware KV Cache Compression for Reasoning Models","created":"2025-05-30","cited_by_count":54,"area":"lr"},{"id":"2505.21906","title":"ChatVLA-2: Vision-Language-Action Model with Open-World Embodied Reasoning from Pretrained Knowledge","created":"2025-05-28","cited_by_count":49,"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":"2505.14183","title":"ThinkSwitcher: When to Think Hard, When to Think Fast","created":"2025-05-20","cited_by_count":37,"area":"lr"},{"id":"2505.15154","title":"Prolonged Reasoning Is Not All You Need: Certainty-Based Adaptive Routing for Efficient LLM/MLLM Reasoning","created":"2025-05-21","cited_by_count":35,"area":"lr"},{"id":"2509.16679","title":"Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle","created":"2025-09-20","cited_by_count":35,"area":null},{"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":"2505.18237","title":"Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens","created":"2025-05-23","cited_by_count":34,"area":"lr"},{"id":"2506.13752","title":"Steering LLM Thinking with Budget Guidance","created":"2025-06-16","cited_by_count":33,"area":"lr"},{"id":"2507.01921","title":"NaturalThoughts: Selecting and Distilling Reasoning Traces for General Reasoning Tasks","created":"2025-07-02","cited_by_count":32,"area":"lr"},{"id":"2505.15182","title":"ReflAct: World-Grounded Decision Making in LLM Agents via Goal-State Reflection","created":"2025-05-21","cited_by_count":31,"area":"agents"},{"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":"2505.24863","title":"AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time","created":"2025-05-30","cited_by_count":29,"area":"lr"},{"id":"2505.13949","title":"FlashThink: An Early Exit Method For Efficient Reasoning","created":"2025-05-20","cited_by_count":28,"area":"lr"},{"id":"2505.23727","title":"PixelThink: Towards Efficient Chain-of-Pixel Reasoning","created":"2025-05-29","cited_by_count":28,"area":"lr"},{"id":"2506.15674","title":"Leaky Thoughts: Large Reasoning Models Are Not Private Thinkers","created":"2025-06-18","cited_by_count":28,"area":"lr"},{"id":"2505.13438","title":"Optimizing Anytime Reasoning via Budget Relative Policy Optimization","created":"2025-05-19","cited_by_count":27,"area":"lr"},{"id":"2505.14604","title":"Let LRMs Break Free from Overthinking via Self-Braking Tuning","created":"2025-05-20","cited_by_count":27,"area":"lr"},{"id":"2505.15400","title":"When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning","created":"2025-05-21","cited_by_count":26,"area":"lr"},{"id":"2505.12284","title":"Shorten After You're Right: Lazy Length Penalties for Reasoning RL","created":"2025-05-18","cited_by_count":25,"area":"lr"},{"id":"2504.13626","title":"Thought Manipulation: External Thought Can Be Efficient for Large Reasoning Models","created":"2025-04-18","cited_by_count":23,"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":"2601.05175","title":"VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice","created":"2026-01-08","cited_by_count":21,"area":"lr"},{"id":"2505.17827","title":"Not All Tokens Are What You Need In Thinking","created":"2025-05-23","cited_by_count":20,"area":"lr"},{"id":"2509.14004","title":"Early Stopping Chain-of-thoughts in Large Language Models","created":"2025-09-17","cited_by_count":20,"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":"2505.22017","title":"The Price of a Second Thought: On the Evaluation of Reasoning Efficiency in Large Language Models","created":"2025-05-28","cited_by_count":18,"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":"2505.19126","title":"MMATH: A Multilingual Benchmark for Mathematical Reasoning","created":"2025-05-25","cited_by_count":17,"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":"2506.09853","title":"Causal Sufficiency and Necessity Improves Chain-of-Thought Reasoning","created":"2025-06-11","cited_by_count":17,"area":"lr"},{"id":"2505.14681","title":"Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training","created":"2025-05-20","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":"2510.10103","title":"Stop When Enough: Adaptive Early-Stopping for Chain-of-Thought Reasoning","created":"2025-10-11","cited_by_count":16,"area":"lr"},{"id":"2507.10616","title":"Scalpel vs. Hammer: GRPO Amplifies Existing Capabilities, SFT Replaces Them","created":"2025-07-13","cited_by_count":15,"area":"lr"},{"id":"2510.24941","title":"Can Aha Moments Be Fake? Towards Quantifying Decorative and True Thinking in Chain-of-Thought","created":"2025-10-28","cited_by_count":15,"area":"lr"},{"id":"2506.12963","title":"Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills","created":"2025-06-15","cited_by_count":14,"area":"lr"},{"id":"2506.23840","title":"Do Thinking Tokens Help or Trap? Towards More Efficient Large Reasoning Model","created":"2025-06-30","cited_by_count":14,"area":"lr"},{"id":"2604.02972","title":"NeuReasoner: Towards Explainable, Controllable, and Unified Reasoning via Mixture-of-Neurons","created":"2026-04-03","cited_by_count":14,"area":"lr"},{"id":"2505.16094","title":"A Survey of Large Language Models for Text-Guided Molecular Discovery: from Molecule Generation to Optimization","created":"2025-05-22","cited_by_count":13,"area":null},{"id":"2505.21825","title":"Let Me Think! A Long Chain-of-Thought Can Be Worth Exponentially Many Short Ones","created":"2025-05-27","cited_by_count":13,"area":"lr"},{"id":"2508.00574","title":"SynAdapt: Learning Adaptive Reasoning in Large Language Models via Synthetic Continuous Chain-of-Thought","created":"2025-08-01","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":"2505.08392","title":"Adaptive GoGI-Skip: Coupling Goal-Gradient Importance with Dynamic Uncertainty for Efficient Reasoning","created":"2025-05-13","cited_by_count":12,"area":"lr"},{"id":"2506.03097","title":"EgoVLM: Policy Optimization for Egocentric Video Understanding","created":"2025-06-03","cited_by_count":12,"area":"lr"},{"id":"2506.05333","title":"Kinetics: Rethinking Test-Time Scaling Laws","created":"2025-06-05","cited_by_count":12,"area":"lr"},{"id":"2506.09260","title":"ThinkQE: Query Expansion via an Evolving Thinking Process","created":"2025-06-10","cited_by_count":12,"area":"lr"},{"id":"2508.02511","title":"Test-time Prompt Intervention","created":"2025-08-04","cited_by_count":12,"area":"lr"},{"id":"2606.07157","title":"Think Fast: Estimating No-CoT Task-Completion Time Horizons of Frontier AI Models","created":"2026-06-05","cited_by_count":12,"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":"2601.14243","title":"Jet-RL: Enabling On-Policy FP8 Reinforcement Learning with Unified Training and Rollout Precision Flow","created":"2026-01-20","cited_by_count":11,"area":"lr"},{"id":"2602.12506","title":"On Robustness and Chain-of-Thought Consistency of RL-Finetuned VLMs","created":"2026-02-13","cited_by_count":11,"area":"lr"},{"id":"2604.16027","title":"Where does output diversity collapse in post-training?","created":"2026-04-17","cited_by_count":11,"area":null},{"id":"2607.00053","title":"SWE-Router: Routing in Multi-turn Agentic Software Engineering Tasks","created":"2026-06-30","cited_by_count":11,"area":"agents"},{"id":"2505.16448","title":"The First Impression Problem: Internal Bias Triggers Overthinking in Reasoning Models","created":"2025-05-22","cited_by_count":10,"area":"lr"},{"id":"2506.08125","title":"Not All Tokens Matter: Towards Efficient LLM Reasoning via Token Significance in Reinforcement Learning","created":"2025-06-09","cited_by_count":10,"area":"lr"},{"id":"2507.00711","title":"Large Reasoning Models are not thinking straight: on the unreliability of thinking trajectories","created":"2025-07-01","cited_by_count":10,"area":"lr"},{"id":"2507.03704","title":"Controlling Thinking Speed in Reasoning Models","created":"2025-07-04","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":"2505.24550","title":"A*-Thought: Efficient Reasoning via Bidirectional Compression for Low-Resource Settings","created":"2025-05-30","cited_by_count":9,"area":"lr"},{"id":"2509.24248","title":"SpecExit: Accelerating Large Reasoning Model via Speculative Exit","created":"2025-09-29","cited_by_count":9,"area":"lr"},{"id":"2511.08525","title":"Investigating CoT Monitorability in Large Reasoning Models","created":"2025-11-11","cited_by_count":9,"area":"lr"},{"id":"2505.11966","title":"Solve-Detect-Verify: Inference-Time Scaling with Flexible Generative Verifier","created":"2025-05-17","cited_by_count":8,"area":"lr"},{"id":"2505.23701","title":"Can LLMs Reason Abstractly Over Math Word Problems Without CoT? Disentangling Abstract Formulation From Arithmetic Computation","created":"2025-05-29","cited_by_count":8,"area":"lr"},{"id":"2506.04182","title":"Long or short CoT? Investigating Instance-level Switch of Large Reasoning Models","created":"2025-06-04","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":"2509.25758","title":"Thinking Sparks!: Emergent Attention Heads in Reasoning Models During Post Training","created":"2025-09-30","cited_by_count":8,"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":"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":"2606.23181","title":"DART: Draft-Agreement Routing for Training-Free Adaptive Thinking Budgets in Hybrid Reasoning Models","created":"2026-06-22","cited_by_count":8,"area":"lr"},{"id":"2505.12992","title":"Fractured Chain-of-Thought Reasoning","created":"2025-05-19","cited_by_count":7,"area":"lr"},{"id":"2505.15276","title":"When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning","created":"2025-05-21","cited_by_count":7,"area":"lr"},{"id":"2505.16216","title":"Memorization or Reasoning? Exploring the Idiom Understanding of LLMs","created":"2025-05-22","cited_by_count":7,"area":"lr"},{"id":"2505.16886","title":"Don't \"Overthink\" Passage Reranking: Is Reasoning Truly Necessary?","created":"2025-05-22","cited_by_count":7,"area":"lr"},{"id":"2505.21908","title":"Reinforcement Learning for Out-of-Distribution Reasoning in LLMs: An Empirical Study on Diagnosis-Related Group Coding","created":"2025-05-28","cited_by_count":7,"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":"2509.05489","title":"Self-Aligned Reward: Towards Effective and Efficient Reasoners","created":"2025-09-05","cited_by_count":7,"area":"lr"},{"id":"2510.11713","title":"Are Large Reasoning Models Interruptible?","created":"2025-10-13","cited_by_count":7,"area":"lr"},{"id":"2601.20467","title":"CtrlCoT: Dual-Granularity Chain-of-Thought Compression for Controllable Reasoning","created":"2026-01-28","cited_by_count":7,"area":"lr"},{"id":"2603.10535","title":"Tackling Length Inflation Without Trade-offs: Group Relative Reward Rescaling for Reinforcement Learning","created":"2026-03-11","cited_by_count":7,"area":"alignment"},{"id":"2605.17672","title":"Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models","created":"2026-05-17","cited_by_count":7,"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":"2505.20296","title":"Reasoning LLMs are Wandering Solution Explorers","created":"2025-05-26","cited_by_count":6,"area":"lr"},{"id":"2509.04474","title":"Scaling Up, Speeding Up: A Benchmark of Speculative Decoding for Efficient LLM Test-Time Scaling","created":"2025-08-30","cited_by_count":6,"area":"lr"},{"id":"2509.23676","title":"From Reasoning to Answer: Empirical, Attention-Based and Mechanistic Insights into Distilled DeepSeek R1 Models","created":"2025-09-28","cited_by_count":6,"area":"lr"},{"id":"2509.23782","title":"Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions","created":"2025-09-28","cited_by_count":6,"area":null},{"id":"2510.09133","title":"On the Provable Performance Guarantee of Efficient Reasoning Models","created":"2025-10-10","cited_by_count":6,"area":"lr"},{"id":"2601.20539","title":"PathWise: Planning through World Model for Automated Heuristic Design via Self-Evolving LLMs","created":"2026-01-28","cited_by_count":6,"area":"wm"}],"next_cursor":"100"}