{"total":53,"rows":[{"id":"2505.22375","title":"Pangu Embedded: An Efficient Dual-system LLM Reasoner with Metacognition","created":"2025-05-28","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":"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":"2508.21048","title":"Veritas: Generalizable Deepfake Detection via Pattern-Aware Reasoning","created":"2025-08-28","cited_by_count":23,"area":"lr"},{"id":"2508.08039","title":"Audio-Thinker: Guiding Audio Language Model When and How to Think via Reinforcement Learning","created":"2025-08-11","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":"2508.21113","title":"R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning","created":"2025-08-28","cited_by_count":18,"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":"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":"2508.11582","title":"Aware First, Think Less: Dynamic Boundary Self-Awareness Drives Extreme Reasoning Efficiency in Large Language Models","created":"2025-08-15","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":"2507.08297","title":"KAT-V1: Kwai-AutoThink Technical Report","created":"2025-07-11","cited_by_count":12,"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":"2602.09953","title":"ATTNPO: Attention-Guided Process Supervision for Efficient Reasoning","created":"2026-02-10","cited_by_count":9,"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":"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":"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":"2601.08310","title":"ORBIT: On-policy Exploration-Exploitation for Controllable Multi-Budget Reasoning","created":"2026-01-13","cited_by_count":7,"area":"lr"},{"id":"2509.26226","title":"Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners","created":"2025-09-30","cited_by_count":5,"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":"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":"2510.19176","title":"The Zero-Step Thinking: An Empirical Study of Mode Selection as Harder Early Exit in Reasoning Models","created":"2025-10-22","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":"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":"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":"2510.03259","title":"Verifying Meta-Awareness via Predictive Rewards in Reasoning Models","created":"2025-09-26","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":"2511.14258","title":"Entropy-Guided Reasoning Compression","created":"2025-11-18","cited_by_count":3,"area":"lr"},{"id":"2603.08659","title":"CODA: Difficulty-Aware Compute Allocation for Adaptive Reasoning","created":"2026-03-09","cited_by_count":3,"area":"lr"},{"id":"2508.12265","title":"Fast, Slow, and Tool-augmented Thinking for LLMs: A Review","created":"2025-08-17","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":"2510.20519","title":"Metis-HOME: Hybrid Optimized Mixture-of-Experts for Multimodal Reasoning","created":"2025-10-23","cited_by_count":2,"area":"lr"},{"id":"2601.21711","title":"TACLer: Tailored Curriculum Reinforcement Learning for Efficient Reasoning","created":"2026-01-29","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":"2608.20256","title":"Learning When to Think: Adaptive Reasoning for Test-Time Compute Allocation","created":"2026-08-20","cited_by_count":2,"area":"lr"},{"id":"2510.14828","title":"RoboGPT-R1: Enhancing Robot Task Planning with Reinforcement Learning","created":"2025-10-16","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":"2602.19519","title":"Ada-RS: Adaptive Rejection Sampling for Selective Thinking","created":"2026-02-23","cited_by_count":1,"area":"lr"},{"id":"2605.31062","title":"AdaptR1: Reinforcement Learning Based Adaptive Interleaved Thinking in Multi-hop Question Answering","created":"2026-05-29","cited_by_count":1,"area":"lr"},{"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":"2604.08232","title":"HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation","created":"2026-04-09","cited_by_count":0,"area":"lr"},{"id":"2605.11625","title":"Nice Fold or Hero Call: Learning Budget-Efficient Thinking for Adaptive Reasoning","created":"2026-05-12","cited_by_count":0,"area":"lr"},{"id":"2606.14591","title":"AudioDER: A Deduplication-Enhanced Reasoning Dataset for Post-Training Large Audio-Language Models","created":"2026-06-12","cited_by_count":0,"area":"lr"},{"id":"2607.08572","title":"Switch-Reasoner: Learn When to Think in Multitask Mixtures via Reinforcement Learning","created":"2026-07-09","cited_by_count":0,"area":"lr"},{"id":"2607.21793","title":"QLPO: Quadrant-weighted Sampling for Length-aware Policy Optimization","created":"2026-07-23","cited_by_count":0,"area":"lr"},{"id":"2607.22622","title":"Learning When to Reason for Text-to-SQL via SFT and DPO","created":"2026-06-17","cited_by_count":0,"area":"lr"},{"id":"2608.26141","title":"AdaThinking-E: One-Token Entropy Regulation for Adaptive Thinking","created":"2026-06-26","cited_by_count":0,"area":"lr"},{"id":"2609.24760","title":"Construting Reverse Thinking: Developing Large Language Models' Reverse Thingking Ability","created":"2026-09-21","cited_by_count":0,"area":"lr"},{"id":"2609.29109","title":"CounterRoute: Self-Routed Reasoning via Hierarchical Counterfactual Credit Assignment","created":"2026-09-24","cited_by_count":0,"area":"lr"},{"id":"2610.11765","title":"Thinking Inertia: LLMs Keep Thinking When Told Not To","created":"2026-10-08","cited_by_count":0,"area":"lr"},{"id":"2610.13081","title":"SWEAR: Section-Wise Efficient Audio Reasoning via Self-Rated Difficulty","created":"2026-10-09","cited_by_count":0,"area":"lr"}],"next_cursor":null}