{"total":131,"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":"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":"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":"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":"2508.10293","title":"Promoting Efficient Reasoning with Verifiable Stepwise Reward","created":"2025-08-14","cited_by_count":28,"area":"lr"},{"id":"2603.01928","title":"LaST-VLA: Thinking in Latent Spatio-Temporal Space for Vision-Language-Action in Autonomous Driving","created":"2026-03-02","cited_by_count":28,"area":"lr"},{"id":"2512.24426","title":"Counterfactual VLA: Self-Reflective Vision-Language-Action Model with Adaptive Reasoning","created":"2025-12-30","cited_by_count":22,"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":"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":"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":"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":"2512.17312","title":"CodeDance: A Dynamic Tool-integrated MLLM for Executable Visual Reasoning","created":"2025-12-19","cited_by_count":16,"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":"2507.06892","title":"Squeeze the Soaked Sponge: Efficient Off-policy Reinforcement Finetuning for Large Language Model","created":"2025-07-09","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":"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":"2508.18773","title":"ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Models","created":"2025-08-26","cited_by_count":11,"area":"lr"},{"id":"2505.21097","title":"Thinker: Learning to Think Fast and Slow","created":"2025-05-27","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":"2510.10977","title":"Revisiting Model Interpolation for Efficient Reasoning","created":"2025-10-13","cited_by_count":10,"area":"lr"},{"id":"2510.01459","title":"LSPO: Length-aware Dynamic Sampling for Policy Optimization in LLM Reasoning","created":"2025-10-01","cited_by_count":9,"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":"2605.02913","title":"Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning","created":"2026-04-08","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":"2510.05040","title":"Test-Time Scaling in Diffusion LLMs via Hidden Semi-Autoregressive Experts","created":"2025-10-06","cited_by_count":8,"area":"lr"},{"id":"2510.08189","title":"R-Horizon: How Far Can Your Large Reasoning Model Really Go in Breadth and Depth?","created":"2025-10-09","cited_by_count":8,"area":"lr"},{"id":"2511.20048","title":"Reducing Latency of LLM Search Agent via Speculation-based Algorithm-System Co-Design","created":"2025-11-25","cited_by_count":8,"area":"lr"},{"id":"2601.03822","title":"ROI-Reasoning: Rational Optimization for Inference via Pre-Computation Meta-Cognition","created":"2026-01-07","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":"2602.11683","title":"ThinkRouter: Efficient Reasoning via Routing Thinking between Latent and Discrete Spaces","created":"2026-02-12","cited_by_count":8,"area":"lr"},{"id":"2605.06908","title":"Same Signal, Opposite Meaning: Direction-Informed Adaptive Learning for LLM Agents","created":"2026-05-07","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":"2507.17307","title":"R-Stitch: Dynamic Trajectory Stitching for Efficient Reasoning","created":"2025-07-23","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":"2509.21070","title":"ScaleDiff: Scaling Difficult Problems for Advanced Mathematical Reasoning","created":"2025-09-25","cited_by_count":6,"area":"lr"},{"id":"2510.12838","title":"A$^2$FM: An Adaptive Agent Foundation Model for Tool-Aware Hybrid Reasoning","created":"2025-10-13","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":"2601.19928","title":"Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and Failures","created":"2026-01-11","cited_by_count":6,"area":"lr"},{"id":"2604.10072","title":"Reason Only When Needed: Efficient Generative Reward Modeling via Model-Internal Uncertainty","created":"2026-04-11","cited_by_count":6,"area":"lr"},{"id":"2507.02663","title":"Think How to Think: Mitigating Overthinking with Autonomous Difficulty Cognition in Large Reasoning Models","created":"2025-07-03","cited_by_count":5,"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":"2510.08026","title":"PEAR: Phase Entropy Aware Reward for Efficient Reasoning","created":"2025-10-09","cited_by_count":5,"area":"lr"},{"id":"2511.01170","title":"DART: Difficulty-Adaptive Reasoning Truncation for Efficient Large Language Models","created":"2025-11-03","cited_by_count":5,"area":"lr"},{"id":"2512.03783","title":"Omni-AutoThink: Adaptive Multimodal Reasoning via Reinforcement Learning","created":"2025-12-03","cited_by_count":5,"area":"lr"},{"id":"2602.12662","title":"Think Fast and Slow: Step-Level Cognitive Depth Adaptation for LLM Agents","created":"2026-02-13","cited_by_count":5,"area":"lr"},{"id":"2606.18089","title":"From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning","created":"2026-06-16","cited_by_count":5,"area":"lr"},{"id":"2508.03363","title":"Thinking with Nothinking Calibration: A New In-Context Learning Paradigm in Reasoning Large Language Models","created":"2025-08-05","cited_by_count":4,"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":"2509.23967","title":"HiPO: Hybrid Policy Optimization for Dynamic Reasoning in LLMs","created":"2025-09-28","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":"2510.08163","title":"ARM2: Adaptive Reasoning Model with Vision Understanding and Executable Code","created":"2025-10-09","cited_by_count":4,"area":"lr"},{"id":"2510.13170","title":"Putting on the Thinking Hats: A Survey on Chain of Thought Fine-tuning from the Perspective of Human Reasoning Mechanism","created":"2025-10-15","cited_by_count":4,"area":"lr"},{"id":"2510.15374","title":"Towards Flash Thinking via Decoupled Advantage Policy Optimization","created":"2025-10-17","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":"2512.01925","title":"Rectifying LLM Thought from Lens of Optimization","created":"2025-12-01","cited_by_count":4,"area":"lr"},{"id":"2601.02972","title":"Correct, Concise and Complete: Multi-stage Training For Adaptive Reasoning","created":"2026-01-06","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":"2602.22556","title":"Stable Adaptive Thinking via Advantage Shaping and Length-Aware Gradient Regulation","created":"2026-02-26","cited_by_count":4,"area":"lr"},{"id":"2604.05164","title":"Not All Turns Are Equally Hard: Adaptive Thinking Budgets For Efficient Multi-Turn Reasoning in Agents","created":"2026-04-06","cited_by_count":4,"area":"lr"},{"id":"2506.09396","title":"Reasoning as a Resource: Optimizing Fast and Slow Thinking in Code Generation Models","created":"2025-06-11","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":"2508.15507","title":"Think in Blocks: Adaptive Reasoning from Direct Response to Deep Reasoning","created":"2025-08-21","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":"2509.25176","title":"SIRI: Scaling Iterative Reinforcement Learning with Interleaved Compression","created":"2025-09-29","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":"2510.06052","title":"MixReasoning: Switching Modes to Think","created":"2025-10-07","cited_by_count":3,"area":"lr"},{"id":"2511.16331","title":"Incorporating Self-Rewriting into Large Language Model Reasoning Reinforcement","created":"2025-11-20","cited_by_count":3,"area":"lr"},{"id":"2512.15274","title":"Well Begun, Half Done: Reinforcement Learning with Prefix Optimization for LLM Reasoning","created":"2025-12-17","cited_by_count":3,"area":"lr"},{"id":"2512.17901","title":"When Reasoning Meets Its Laws","created":"2025-12-19","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":"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"},{"id":"2603.08659","title":"CODA: Difficulty-Aware Compute Allocation for Adaptive Reasoning","created":"2026-03-09","cited_by_count":3,"area":"lr"},{"id":"2607.05861","title":"Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization","created":"2026-07-07","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":"2510.01581","title":"Think Right: Learning to Mitigate Under-Over Thinking via Adaptive, Attentive Compression","created":"2025-10-02","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":"2511.03328","title":"Benchmarking the Thinking Mode of Multimodal Large Language Models in Clinical Tasks","created":"2025-11-05","cited_by_count":2,"area":"lr"},{"id":"2601.03969","title":"Anti-Length Shift: Dynamic Outlier Truncation for Training Efficient Reasoning Models","created":"2026-01-07","cited_by_count":2,"area":"lr"},{"id":"2601.09260","title":"Efficient Paths and Dense Rewards: Probabilistic Flow Reasoning for Large Language Models","created":"2026-01-14","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":"2602.09555","title":"Adaptive Test-Time Compute Allocation for Block Diffusion Language Models in Complex Reasoning","created":"2026-02-10","cited_by_count":2,"area":"lr"},{"id":"2602.11639","title":"PACE: Prefix-Protected and Difficulty-Aware Compression for Efficient Reasoning","created":"2026-02-12","cited_by_count":2,"area":"lr"},{"id":"2603.13348","title":"AutoTool: Automatic Scaling of Tool-Use Capabilities in RL via Decoupled Entropy Constraints","created":"2026-03-07","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":"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":"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":"2601.07238","title":"Group Pattern Selection Optimization: Let LRMs Pick the Right Pattern for Reasoning","created":"2026-01-12","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"}],"next_cursor":"100"}