{"total":111,"rows":[{"id":"2504.14945","title":"Learning to Reason under Off-Policy Guidance","created":"2025-04-21","cited_by_count":281,"area":"lr"},{"id":"2503.24235","title":"A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?","created":"2025-03-31","cited_by_count":223,"area":"lr"},{"id":"2506.23918","title":"Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers","created":"2025-06-30","cited_by_count":199,"area":"lr"},{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2505.08617","title":"OpenThinkIMG: Learning to Think with Images via Visual Tool Reinforcement Learning","created":"2025-05-13","cited_by_count":163,"area":"lr"},{"id":"2504.10903","title":"Efficient Reasoning Models: A Survey","created":"2025-04-15","cited_by_count":95,"area":"lr"},{"id":"2504.21370","title":"ShorterBetter: Guiding Reasoning Models to Find Optimal Inference Length for Efficient Reasoning","created":"2025-04-30","cited_by_count":72,"area":"lr"},{"id":"2504.17704","title":"Safety in Large Reasoning Models: A Survey","created":"2025-04-24","cited_by_count":64,"area":"lr"},{"id":"2504.06514","title":"Missing Premise exacerbates Overthinking: Are Reasoning Models losing Critical Thinking Skill?","created":"2025-04-09","cited_by_count":58,"area":"lr"},{"id":"2506.04207","title":"Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning","created":"2025-06-04","cited_by_count":53,"area":"lr"},{"id":"2510.02245","title":"ExGRPO: Learning to Reason from Experience","created":"2025-10-02","cited_by_count":53,"area":"lr"},{"id":"2506.08446","title":"A Survey on Large Language Models for Mathematical Reasoning","created":"2025-06-10","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":"2509.02350","title":"Implicit Reasoning in Large Language Models: A Comprehensive Survey","created":"2025-09-02","cited_by_count":43,"area":"lr"},{"id":"2509.24304","title":"FrameThinker: Learning to Think with Long Videos via Multi-Turn Frame Spotlighting","created":"2025-09-29","cited_by_count":42,"area":"lr"},{"id":"2510.09285","title":"Spotlight on Token Perception for Multimodal Reinforcement Learning","created":"2025-10-10","cited_by_count":39,"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":"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":"2503.24377","title":"Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models","created":"2025-03-31","cited_by_count":36,"area":"lr"},{"id":"2505.04881","title":"ConCISE: Confidence-guided Compression in Step-by-step Efficient Reasoning","created":"2025-05-08","cited_by_count":33,"area":"lr"},{"id":"2510.25760","title":"Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarks","created":"2025-10-29","cited_by_count":33,"area":"lr"},{"id":"2508.05988","title":"Pruning the Unsurprising: Efficient LLM Reasoning via First-Token Surprisal","created":"2025-08-08","cited_by_count":32,"area":"lr"},{"id":"2507.02076","title":"Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs","created":"2025-07-02","cited_by_count":31,"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":"2505.21600","title":"R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing","created":"2025-05-27","cited_by_count":29,"area":"lr"},{"id":"2505.14810","title":"Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models","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":"2505.18962","title":"System-1.5 Reasoning: Traversal in Language and Latent Spaces with Dynamic Shortcuts","created":"2025-05-25","cited_by_count":27,"area":"lr"},{"id":"2509.03871","title":"A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models","created":"2025-09-04","cited_by_count":25,"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":"2510.01833","title":"Plan Then Action:High-Level Planning Guidance Reinforcement Learning for LLM Reasoning","created":"2025-10-02","cited_by_count":19,"area":"lr"},{"id":"2512.24165","title":"DiffThinker: Towards Generative Multimodal Reasoning with Diffusion Models","created":"2025-12-30","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":"2505.15684","title":"ThinkLess: A Training-Free Inference-Efficient Method for Reducing Reasoning Redundancy","created":"2025-05-21","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":"2510.08457","title":"ARES: Multimodal Adaptive Reasoning via Difficulty-Aware Token-Level Entropy Shaping","created":"2025-10-09","cited_by_count":17,"area":"lr"},{"id":"2601.05110","title":"GlimpRouter: Efficient Collaborative Inference by Glimpsing One Token of Thoughts","created":"2026-01-08","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":"2504.13828","title":"Generative AI Act II: Test Time Scaling Drives Cognition Engineering","created":"2025-04-18","cited_by_count":15,"area":"lr"},{"id":"2505.19716","title":"Concise Reasoning, Big Gains: Pruning Long Reasoning Trace with Difficulty-Aware Prompting","created":"2025-05-26","cited_by_count":15,"area":"lr"},{"id":"2505.19684","title":"VisCRA: A Visual Chain Reasoning Attack for Jailbreaking Multimodal Large Language Models","created":"2025-05-26","cited_by_count":13,"area":"lr"},{"id":"2506.08390","title":"On Reasoning Strength Planning in Large Reasoning Models","created":"2025-06-10","cited_by_count":13,"area":"lr"},{"id":"2504.14560","title":"ReasoningV: Efficient Verilog Code Generation with Adaptive Hybrid Reasoning Model","created":"2025-04-20","cited_by_count":12,"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":"2505.20223","title":"Chain-of-Thought for Autonomous Driving: A Comprehensive Survey and Future Prospects","created":"2025-05-26","cited_by_count":12,"area":"lr"},{"id":"2506.02532","title":"ReasoningFlow: Semantic Structure of Complex Reasoning Traces","created":"2025-06-03","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":"2507.01551","title":"Self-Guided Process Reward Optimization with Redefined Step-wise Advantage for Process Reinforcement Learning","created":"2025-07-02","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":"2504.10368","title":"Exploring the System 1 Thinking Capability of Large Reasoning Models","created":"2025-04-14","cited_by_count":10,"area":"lr"},{"id":"2506.12353","title":"Efficient Reasoning Through Suppression of Self-Affirmation Reflections in Large Reasoning Models","created":"2025-06-14","cited_by_count":10,"area":"lr"},{"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":"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":"2510.08483","title":"DeepPrune: Parallel Scaling without Inter-trace Redundancy","created":"2025-10-09","cited_by_count":10,"area":"lr"},{"id":"2601.14888","title":"What Makes Low-Bit Quantization-Aware Training Work for Reasoning LLMs? A Systematic Study","created":"2026-01-21","cited_by_count":10,"area":"lr"},{"id":"2602.15382","title":"The Vision Wormhole: Latent-Space Communication in Heterogeneous Multi-Agent Systems","created":"2026-02-17","cited_by_count":9,"area":"lr"},{"id":"2604.04902","title":"Are Latent Reasoning Models Easily Interpretable?","created":"2026-04-06","cited_by_count":9,"area":"lr"},{"id":"2504.10766","title":"How Instruction and Reasoning Data shape Post-Training: Data Quality through the Lens of Layer-wise Gradients","created":"2025-04-14","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":"2507.03133","title":"ReliableMath: Benchmark of Reliable Mathematical Reasoning on Large Language Models","created":"2025-07-03","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":"2507.04348","title":"SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control","created":"2025-07-06","cited_by_count":7,"area":"lr"},{"id":"2508.18260","title":"MIRAGE: Scaling Test-Time Inference with Parallel Graph-Retrieval-Augmented Reasoning Chains","created":"2025-08-25","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":"2505.19862","title":"REA-RL: Reflection-Aware Online Reinforcement Learning for Efficient Reasoning","created":"2025-05-26","cited_by_count":6,"area":"lr"},{"id":"2508.16383","title":"GLARE: Agentic Reasoning for Legal Judgment Prediction","created":"2025-08-22","cited_by_count":6,"area":"lr"},{"id":"2510.00494","title":"Exploring System 1 and 2 communication for latent reasoning in LLMs","created":"2025-10-01","cited_by_count":6,"area":"lr"},{"id":"2512.12387","title":"Anchoring Values in Temporal and Group Dimensions for Flow Matching Model Alignment","created":"2025-12-13","cited_by_count":6,"area":"lr"},{"id":"2506.05936","title":"DynamicMind: A Tri-Mode Thinking System for Large Language Models","created":"2025-06-06","cited_by_count":5,"area":"lr"},{"id":"2507.04023","title":"Do LLMs Overthink Basic Math Reasoning? Benchmarking the Accuracy-Efficiency Tradeoff in Language Models","created":"2025-07-05","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":"2606.08708","title":"PRPO: Perception-Reinforced Policy Optimization via Token-Level Dynamic Advantage Reshaping","created":"2026-06-07","cited_by_count":5,"area":"lr"},{"id":"2507.20150","title":"The Policy Cliff: A Theoretical Analysis of Reward-Policy Maps in Large Language Models","created":"2025-07-27","cited_by_count":3,"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":"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":"2509.23633","title":"Fast Thinking for Large Language Models","created":"2025-09-28","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":"2601.03649","title":"SyncThink: A Training-Free Strategy to Align Inference Termination with Reasoning Saturation","created":"2026-01-07","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":"2603.04002","title":"Discriminative Perception via Anchored Description for Reasoning Segmentation","created":"2026-03-04","cited_by_count":3,"area":"lr"},{"id":"2505.19815","title":"Deciphering Trajectory-Aided LLM Reasoning: An Optimization Perspective","created":"2025-05-26","cited_by_count":2,"area":"lr"},{"id":"2505.23059","title":"From Token to Action: State Machine Reasoning to Mitigate Overthinking in Information Retrieval","created":"2025-05-29","cited_by_count":2,"area":"lr"},{"id":"2509.22144","title":"From Long to Lean: Performance-aware and Adaptive Chain-of-Thought Compression via Multi-round Refinement","created":"2025-09-26","cited_by_count":2,"area":"lr"},{"id":"2601.12748","title":"Towards Robust Process Reward Modeling via Noise-aware Learning","created":"2026-01-19","cited_by_count":2,"area":"lr"},{"id":"2602.12113","title":"Stop Unnecessary Reflection: Training LRMs for Efficient Reasoning with Adaptive Reflection and Length Coordinated Penalty","created":"2026-02-12","cited_by_count":2,"area":"lr"},{"id":"2604.05355","title":"ETR: Entropy Trend Reward for Efficient Chain-of-Thought Reasoning","created":"2026-04-07","cited_by_count":2,"area":"lr"},{"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":"2509.21960","title":"Think Smart, Not Hard: Difficulty Adaptive Reasoning for Large Audio Language Models","created":"2025-09-26","cited_by_count":1,"area":"lr"},{"id":"2509.24836","title":"Logical Structure as Knowledge: Enhancing LLM Reasoning via Structured Logical Knowledge Density Estimation","created":"2025-09-29","cited_by_count":1,"area":"lr"},{"id":"2512.19135","title":"Understanding Chain-of-Thought in Large Language Models via Topological Data Analysis","created":"2025-12-22","cited_by_count":1,"area":"lr"},{"id":"2601.04805","title":"Thinking-Based Non-Thinking: Solving the Reward Hacking Problem in Training Hybrid Reasoning Models via Reinforcement Learning","created":"2026-01-08","cited_by_count":1,"area":"lr"},{"id":"2604.09150","title":"Think Less, Know More: State-Aware Reasoning Compression with Knowledge Guidance for Efficient Reasoning","created":"2026-04-10","cited_by_count":1,"area":"lr"},{"id":"2604.18307","title":"Reasoning Models Know What's Important, and Encode It in Their Activations","created":"2026-04-20","cited_by_count":1,"area":"lr"},{"id":"2605.14358","title":"Uncovering the Representation Geometry of Minimal Cores in Overcomplete Reasoning Traces","created":"2026-05-14","cited_by_count":1,"area":"lr"},{"id":"2607.00862","title":"CAT: Confidence-Adaptive Thinking for Efficient Reasoning of Large Reasoning Models","created":"2026-07-01","cited_by_count":1,"area":"lr"},{"id":"2508.12897","title":"RAJ-PGA: Reasoning-Activated Jailbreak and Principle-Guided Alignment Framework for Large Reasoning Models","created":"2025-08-18","cited_by_count":0,"area":"lr"},{"id":"2510.09358","title":"Boosting Multi-modal Keyphrase Prediction with Dynamic Chain-of-Thought in Vision-Language Models","created":"2025-10-10","cited_by_count":0,"area":"lr"},{"id":"2512.14332","title":"Step-Tagging: Toward controlling the generation of Language Reasoning Models through step monitoring","created":"2025-12-16","cited_by_count":0,"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"}],"next_cursor":"100"}