{"total":66,"rows":[{"id":"2603.05433","title":"CRISP: Compressed Reasoning via Iterative Self-Policy Distillation","created":"2026-03-05","cited_by_count":58,"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":"2509.21128","title":"RL Squeezes, SFT Expands: A Comparative Study of Reasoning LLMs","created":"2025-09-25","cited_by_count":34,"area":"lr"},{"id":"2509.19284","title":"What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoT","created":"2025-09-23","cited_by_count":25,"area":"lr"},{"id":"2604.05655","title":"LLM Reasoning as Trajectories: Step-Specific Representation Geometry and Correctness Signals","created":"2026-04-07","cited_by_count":24,"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":"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":"2507.06167","title":"Skywork-R1V3 Technical Report","created":"2025-07-08","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":"2508.02178","title":"Reconsidering Overthinking: Penalizing Internal and External Redundancy in CoT Reasoning","created":"2025-08-04","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":"2511.10788","title":"From Efficiency to Adaptivity: A Deeper Look at Adaptive Reasoning in Large Language Models","created":"2025-11-13","cited_by_count":12,"area":"lr"},{"id":"2602.02140","title":"Quantifying the Gap between Understanding and Generation within Unified Multimodal Models","created":"2026-02-02","cited_by_count":12,"area":null},{"id":"2506.18810","title":"ConciseHint: Boosting Efficient Reasoning via Continuous Concise Hints during Generation","created":"2025-06-23","cited_by_count":10,"area":"lr"},{"id":"2601.23045","title":"The Hot Mess of AI: How Does Misalignment Scale With Model Intelligence and Task Complexity?","created":"2026-01-30","cited_by_count":10,"area":null},{"id":"2510.25206","title":"RAVR: Reference-Answer-guided Variational Reasoning for Large Language Models","created":"2025-10-29","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":"2510.11713","title":"Are Large Reasoning Models Interruptible?","created":"2025-10-13","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":"2508.17291","title":"Meta-R1: Empowering Large Reasoning Models with Metacognition","created":"2025-08-24","cited_by_count":6,"area":"lr"},{"id":"2512.02874","title":"Think in Parallel, Answer as One: Logit Averaging for Open-Ended Reasoning","created":"2025-12-02","cited_by_count":6,"area":"lr"},{"id":"2512.05325","title":"LYNX: Learning Dynamic Exits for Confidence-Controlled Reasoning","created":"2025-12-05","cited_by_count":6,"area":"lr"},{"id":"2601.07036","title":"Mid-Think: Training-Free Intermediate-Budget Reasoning via Token-Level Triggers","created":"2026-01-11","cited_by_count":6,"area":"lr"},{"id":"2602.08324","title":"Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression","created":"2026-02-09","cited_by_count":6,"area":"lr"},{"id":"2603.14251","title":"Mitigating Overthinking in Large Reasoning Language Models via Reasoning Path Deviation Monitoring","created":"2026-03-15","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":"2509.20868","title":"StyleBench: Evaluating thinking styles in Large Language Models","created":"2025-09-25","cited_by_count":5,"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":"2508.04460","title":"From \"Aha Moments\" to Controllable Thinking: Toward Meta-Cognitive Reasoning in Large Reasoning Models via Decoupled Reasoning and Control","created":"2025-08-06","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":"2510.02249","title":"Explore Briefly, Then Decide: Mitigating LLM Overthinking via Cumulative Entropy Regulation","created":"2025-10-02","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":"2603.12372","title":"Efficient Reasoning with Balanced Thinking","created":"2026-03-12","cited_by_count":4,"area":"lr"},{"id":"2604.21764","title":"Thinking with Reasoning Skills: Fewer Tokens, More Accuracy","created":"2026-04-23","cited_by_count":4,"area":"lr"},{"id":"2510.06052","title":"MixReasoning: Switching Modes to Think","created":"2025-10-07","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":"2512.13979","title":"ReflCtrl: Controlling LLM Reflection Efficiently via Representation Engineering","created":"2025-12-16","cited_by_count":3,"area":"lr"},{"id":"2602.02010","title":"NEAT: Neuron-Based Early Exit for Large Reasoning Models","created":"2026-02-02","cited_by_count":3,"area":"lr"},{"id":"2603.13274","title":"Learning from Partial Chain-of-Thought via Truncated-Reasoning Self-Distillation","created":"2026-02-27","cited_by_count":3,"area":"lr"},{"id":"2606.22716","title":"Beyond Penalizing Mistakes: Stabilizing Efficiency Training in Large Reasoning Models via Adaptive Correct-Only Rewards","created":"2026-06-21","cited_by_count":3,"area":"lr"},{"id":"2607.22629","title":"Masked Distillation: Internalizing the Chain-of-Thought in Language Models","created":"2026-06-18","cited_by_count":3,"area":"lr"},{"id":"2609.30652","title":"Recursive Self-Improvement via On-Policy Distillation for Reasoning","created":"2026-09-25","cited_by_count":3,"area":"distill"},{"id":"2509.22546","title":"Think Socially via Cognitive Reasoning","created":"2025-09-26","cited_by_count":2,"area":"lr"},{"id":"2510.17045","title":"Video Reasoning without Training","created":"2025-10-19","cited_by_count":2,"area":"lr"},{"id":"2511.17487","title":"Downscaling Intelligence: Exploring Perception and Reasoning Bottlenecks in Small Multimodal Models","created":"2025-11-21","cited_by_count":2,"area":"lr"},{"id":"2602.01999","title":"From Latent Signals to Reflection Behavior: Tracing Meta-Cognitive Activation Trajectory in R1-Style LLMs","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2604.07922","title":"SAT: Balancing Reasoning Accuracy and Efficiency with Stepwise Adaptive Thinking","created":"2026-04-09","cited_by_count":2,"area":"lr"},{"id":"2608.04771","title":"Fewer Tokens, Smaller Cache: Reward-Coordinated Efficient Reasoning","created":"2026-08-05","cited_by_count":2,"area":"lr"},{"id":"2601.17421","title":"Oops, Wait: Discourse Tokens Matter in Reasoning Model","created":"2026-01-24","cited_by_count":1,"area":"lr"},{"id":"2601.22617","title":"EntroCut: Entropy-Guided Adaptive Truncation for Efficient Chain-of-Thought Reasoning in Small-scale Large Reasoning Models","created":"2026-01-30","cited_by_count":1,"area":"lr"},{"id":"2602.06454","title":"RelayGen: Intra-Generation Model Switching for Efficient Reasoning","created":"2026-02-06","cited_by_count":1,"area":"lr"},{"id":"2602.15778","title":"*-PLUIE: Personalisable metric with Llm Used for Improved Evaluation","created":"2026-02-17","cited_by_count":1,"area":null},{"id":"2602.20904","title":"Transcoder Adapters for Reasoning-Model Diffing","created":"2026-02-24","cited_by_count":1,"area":"lr"},{"id":"2508.13654","title":"Input-Time Scaling: Adding Noise and Irrelevance into Less-Is-More Drastically Improves Reasoning Performance and Efficiency","created":"2025-08-19","cited_by_count":0,"area":"lr"},{"id":"2510.07974","title":"Active Confusion Expression in Large Language Models: Leveraging World Models toward Better Social Reasoning","created":"2025-10-09","cited_by_count":0,"area":"wm"},{"id":"2510.10528","title":"Merlin's Whisper: Enabling Efficient Reasoning in Large Language Models via Black-box Persuasive Prompting","created":"2025-10-12","cited_by_count":0,"area":"lr"},{"id":"2601.22484","title":"Mitigating Cognitive Inertia in Large Reasoning Models via Latent Spike Steering","created":"2026-01-30","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":"2605.28305","title":"Revisiting Anthropomorphic Reflection Markers in Large Language Model Reasoning","created":"2026-05-27","cited_by_count":0,"area":"lr"},{"id":"2606.07108","title":"DyCon: Dynamic Reasoning Control via Evolving Difficulty Modeling","created":"2026-06-05","cited_by_count":0,"area":"lr"},{"id":"2608.15065","title":"Funnel of Thoughts: Efficient Test-Time Scaling via Early Voting and Rollout Pruning","created":"2026-08-15","cited_by_count":0,"area":"lr"},{"id":"2609.07103","title":"Revisiting Complete Reasoning Traces for Post-Training","created":"2026-09-07","cited_by_count":0,"area":"lr"},{"id":"2609.40360","title":"Semifactual Credit-Augmented Policy Optimization","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.18862","title":"DoubtLess: Training-Free Contrastive Decoding for Efficient Reasoning","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}