{"total":98,"rows":[{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2507.14417","title":"Inverse Scaling in Test-Time Compute","created":"2025-07-19","cited_by_count":50,"area":"lr"},{"id":"2507.21848","title":"EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity","created":"2025-07-29","cited_by_count":41,"area":"lr"},{"id":"2508.13141","title":"OptimalThinkingBench: Evaluating Over and Underthinking in LLMs","created":"2025-08-18","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":"2505.24863","title":"AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time","created":"2025-05-30","cited_by_count":29,"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":"2506.07240","title":"Overclocking LLM Reasoning: Monitoring and Controlling Thinking Path Lengths in LLMs","created":"2025-06-08","cited_by_count":22,"area":"lr"},{"id":"2602.13517","title":"Think Deep, Not Just Long: Measuring LLM Reasoning Effort via Deep-Thinking Tokens","created":"2026-02-13","cited_by_count":22,"area":"lr"},{"id":"2512.16918","title":"AdaTooler-V: Adaptive Tool-Use for Images and Videos","created":"2025-12-18","cited_by_count":21,"area":"lr"},{"id":"2505.18298","title":"Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards","created":"2025-05-23","cited_by_count":20,"area":"lr"},{"id":"2505.19970","title":"CP-Router: An Uncertainty-Aware Router Between LLM and LRM","created":"2025-05-26","cited_by_count":20,"area":"lr"},{"id":"2510.02212","title":"DiFFPO: Training Diffusion LLMs to Reason Fast and Furious via Reinforcement Learning","created":"2025-10-02","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":"2508.17627","title":"The Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics Analysis","created":"2025-08-25","cited_by_count":18,"area":"lr"},{"id":"2505.20013","title":"WebCoT: Enhancing Web Agent Reasoning by Reconstructing Chain-of-Thought in Reflection, Branching, and Rollback","created":"2025-05-26","cited_by_count":17,"area":"lr"},{"id":"2601.14209","title":"InT: Self-Proposed Interventions Enable Credit Assignment in LLM Reasoning","created":"2026-01-20","cited_by_count":14,"area":"lr"},{"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":"2606.00206","title":"Quantized Reasoning Models Think They Need to Think Longer, but They Do Not","created":"2026-05-29","cited_by_count":10,"area":"lr"},{"id":"2508.15842","title":"Lexical Hints of Accuracy in LLM Reasoning Chains","created":"2025-08-19","cited_by_count":9,"area":"lr"},{"id":"2510.20665","title":"The Shape of Reasoning: Topological Analysis of Reasoning Traces in Large Language Models","created":"2025-10-23","cited_by_count":9,"area":"lr"},{"id":"2507.21476","title":"Which LLMs Get the Joke? Probing Non-STEM Reasoning Abilities with HumorBench","created":"2025-07-29","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":"2510.27072","title":"Towards Understanding Self-play for LLM Reasoning","created":"2025-10-31","cited_by_count":8,"area":"lr"},{"id":"2507.02822","title":"SynapseRoute: An Auto-Route Switching Framework on Dual-State Large Language Model","created":"2025-07-03","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":"2601.23163","title":"Probing the Trajectories of Reasoning Traces in Large Language Models","created":"2026-01-30","cited_by_count":7,"area":"lr"},{"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":"2505.13326","title":"Thinking Short and Right Over Thinking Long: Serving LLM Reasoning Efficiently and Accurately","created":"2025-05-19","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":"2509.25426","title":"RADAR: Reasoning-Ability and Difficulty-Aware Routing for Reasoning LLMs","created":"2025-09-29","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":"2601.19928","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":"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":"2602.13935","title":"Statistical Early Stopping for Reasoning Models","created":"2026-02-15","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":"2605.25864","title":"When Self-Belief Misleads: Active Label Acquisition for Reinforcement Learning with Verifiable Rewards","created":"2026-05-25","cited_by_count":6,"area":"lr"},{"id":"2506.11077","title":"CyclicReflex: Improving Reasoning Models via Cyclical Reflection Token Scheduling","created":"2025-06-04","cited_by_count":5,"area":"lr"},{"id":"2602.14798","title":"Overthinking Loops in Agents: A Structural Risk via MCP Tools","created":"2026-02-16","cited_by_count":5,"area":"lr"},{"id":"2607.28374","title":"LEDGERMIND: Provenance-Constrained Multimodal Agentic Reasoning with a Structured Evidence Ledger","created":"2026-07-30","cited_by_count":5,"area":"lr"},{"id":"2510.03605","title":"Understanding the Role of Training Data in Test-Time Scaling","created":"2025-10-04","cited_by_count":4,"area":"lr"},{"id":"2510.03805","title":"Beyond Token Length: Step Pruner for Efficient and Accurate Reasoning in Large Language Models","created":"2025-10-04","cited_by_count":4,"area":"lr"},{"id":"2602.09591","title":"On the Optimal Reasoning Length for RL-Trained Language Models","created":"2026-02-10","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":"2509.00971","title":"CoreThink: A Symbolic Reasoning Layer to reason over Long Horizon Tasks with LLMs","created":"2025-08-31","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":"2510.12063","title":"ThinkPilot: Steering Reasoning Models via Automated Think-prefixes Optimization","created":"2025-10-14","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":"2512.13979","title":"ReflCtrl: Controlling LLM Reflection Efficiently via Representation Engineering","created":"2025-12-16","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":"2602.19281","title":"Limited Reasoning Space: The cage of long-horizon reasoning in LLMs","created":"2026-02-22","cited_by_count":3,"area":"lr"},{"id":"2604.01161","title":"Reasoning Shift: How Context Silently Shortens LLM Reasoning","created":"2026-04-01","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":"2505.22290","title":"Rethinking the Unsolvable: When In-Context Search Meets Test-Time Scaling","created":"2025-05-28","cited_by_count":2,"area":"lr"},{"id":"2508.12604","title":"SSPO: Self-traced Step-wise Preference Optimization for Process Supervision and Reasoning Compression","created":"2025-08-18","cited_by_count":2,"area":"lr"},{"id":"2509.24560","title":"AdaThink-Med: Optimizing Inference-Time Compute for Medical Reasoning via Uncertainty Quantification","created":"2025-09-29","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":"2510.17062","title":"Investigating Thinking Behaviours of Reasoning-Based Language Models for Social Bias Mitigation","created":"2025-10-20","cited_by_count":2,"area":"lr"},{"id":"2511.03408","title":"Efficient Reasoning via Thought-Training and Thought-Free Inference","created":"2025-11-05","cited_by_count":2,"area":"lr"},{"id":"2602.09832","title":"LLM Reasoning Predicts When Models Are Right: Evidence from Coding Classroom Discourse","created":"2026-02-10","cited_by_count":2,"area":"lr"},{"id":"2602.14917","title":"BFS-PO: Best-First Search for Large Reasoning Models","created":"2026-02-16","cited_by_count":2,"area":"lr"},{"id":"2605.15454","title":"Reasoning Models Don't Just Think Longer, They Move Differently","created":"2026-05-14","cited_by_count":2,"area":"lr"},{"id":"2606.02218","title":"Faster Synchronous On-Policy RL via Straggler-Aware Group Sizing","created":"2026-06-01","cited_by_count":2,"area":"lr"},{"id":"2606.21943","title":"Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning","created":"2026-06-20","cited_by_count":2,"area":"lr"},{"id":"2509.17000","title":"Adaptive Overclocking: Dynamic Control of Thinking Path Length via Real-Time Reasoning Signals","created":"2025-09-21","cited_by_count":1,"area":"lr"},{"id":"2510.08647","title":"Can Reasoning Path still be Effective as Input? Bridging Post-Reasoning to Chain-of-Thought Compression","created":"2025-10-09","cited_by_count":1,"area":"lr"},{"id":"2601.03630","title":"Reasoning Model Is Superior LLM-Judge, Yet Suffers from Biases","created":"2026-01-07","cited_by_count":1,"area":"lr"},{"id":"2601.22735","title":"MM-THEBench: Do Reasoning MLLMs Think Reasonably?","created":"2026-01-30","cited_by_count":1,"area":"lr"},{"id":"2605.07316","title":"Implicit Compression Regularization: Concise Reasoning via Internal Shorter Distributions in RL Post-Training","created":"2026-05-08","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":"2605.15764","title":"GRASP: Learning to Ground Social Reasoning in Multi-Person Non-Verbal Interactions","created":"2026-05-15","cited_by_count":1,"area":"lr"},{"id":"2606.00376","title":"The Deterministic Horizon: When Extended Reasoning Fails and Tool Delegation Becomes Necessary","created":"2026-05-29","cited_by_count":1,"area":"lr"},{"id":"2606.17890","title":"Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models","created":"2026-06-16","cited_by_count":1,"area":"lr"},{"id":"2607.00482","title":"Know When to Stop: Segment-Level Credit Assignment for Reducing Overthinking","created":"2026-07-01","cited_by_count":1,"area":"lr"},{"id":"2607.01571","title":"Geometric Signatures of Reasoning: A Spectral Perspective on Task Hardness","created":"2026-07-02","cited_by_count":1,"area":"lr"},{"id":"2608.03401","title":"Shorter Reasoning, Earlier Answers? An Evaluation of Reasoning Interfaces","created":"2026-08-04","cited_by_count":1,"area":"lr"},{"id":"2512.19585","title":"Increasing the Thinking Budget is Not All You Need","created":"2025-12-22","cited_by_count":0,"area":"lr"},{"id":"2601.09089","title":"SubTokenTest: A Practical Benchmark for Real-World Sub-token Understanding","created":"2026-01-14","cited_by_count":0,"area":"lr"},{"id":"2602.00760","title":"APR: Penalizing Structural Redundancy in Large Reasoning Models via Anchor-based Process Rewards","created":"2026-01-31","cited_by_count":0,"area":"lr"},{"id":"2602.01120","title":"MarkovScale: Towards Optimal Sequential Scaling at Inference Time","created":"2026-02-01","cited_by_count":0,"area":"lr"},{"id":"2603.18533","title":"Balancing the Reasoning Load: Difficulty-Differentiated Policy Optimization with Length Redistribution for Efficient and Robust Reinforcement Learning","created":"2026-03-19","cited_by_count":0,"area":"lr"},{"id":"2603.27226","title":"Rethinking Easy-to-Hard: Limits of Curriculum Learning in Post-Training for Deductive Reasoning","created":"2026-03-28","cited_by_count":0,"area":"lr"},{"id":"2604.02007","title":"Apriel-Reasoner: RL Post-Training for General-Purpose and Efficient Reasoning","created":"2026-04-02","cited_by_count":0,"area":"lr"},{"id":"2605.22211","title":"CLORE: Content-Level Optimization for Reasoning Efficiency","created":"2026-05-21","cited_by_count":0,"area":"lr"},{"id":"2605.23074","title":"PathCal: State-Aware Reflection-Marker Calibration for Efficient Reasoning","created":"2026-05-21","cited_by_count":0,"area":"lr"},{"id":"2606.03217","title":"An Asymptotic Theory of Chain-of-Thought in In-Context Learning","created":"2026-06-02","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":"2606.19927","title":"CARE: Competence-Aware Reward Shaping for Adaptive Reasoning Length in Video-MLLMs","created":"2026-06-18","cited_by_count":0,"area":"lr"},{"id":"2607.21616","title":"Lost in Context: Addressing Context Anxiety in Large Language Models","created":"2026-05-29","cited_by_count":0,"area":"lr"},{"id":"2608.01319","title":"Cognitive Demand Steering for Adaptive Meta-Reasoning in Large Language Models","created":"2026-08-02","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":"2608.25583","title":"GRIP: Granular Reward-Guided Parameter Interpolation for Efficient Reasoning","created":"2026-08-26","cited_by_count":0,"area":"lr"},{"id":"2608.26442","title":"Don't Overthink, Don't Underthink: Toward Adaptive Reasoning in Agentic AI","created":"2026-08-26","cited_by_count":0,"area":"lr"},{"id":"2608.28600","title":"SHAPE of Chain-of-Thought in Math Reasoning","created":"2026-06-28","cited_by_count":0,"area":"lr"},{"id":"2609.21247","title":"When Does Reasoning Help in Machine Translation? A Hierarchical Analysis of LRM Reasoning Traces","created":"2026-09-18","cited_by_count":0,"area":"lr"},{"id":"2609.27166","title":"Scaling of Capability and Efficiency at Inference Time in Large Reasoning Models","created":"2026-09-22","cited_by_count":0,"area":"lr"},{"id":"2609.29664","title":"To Think or Not to Think: Allocating Reasoning Where It Helps","created":"2026-08-30","cited_by_count":0,"area":"lr"},{"id":"2610.19890","title":"Frustratingly Easy Majority Voting Using Length Conditioning","created":"2026-10-14","cited_by_count":0,"area":"lr"}],"next_cursor":null}