{"total":61,"rows":[{"id":"2502.17419","title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","created":"2025-02-24","cited_by_count":320,"area":"lr"},{"id":"2506.14245","title":"Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs","created":"2025-06-17","cited_by_count":289,"area":"lr"},{"id":"2507.01352","title":"Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy","created":"2025-07-02","cited_by_count":214,"area":"lr"},{"id":"2505.11896","title":"AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning","created":"2025-05-17","cited_by_count":87,"area":"lr"},{"id":"2502.07316","title":"CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction","created":"2025-02-11","cited_by_count":55,"area":"lr"},{"id":"2502.00334","title":"UGPhysics: A Comprehensive Benchmark for Undergraduate Physics Reasoning with Large Language Models","created":"2025-02-01","cited_by_count":48,"area":"lr"},{"id":"2412.06394","title":"GameArena: Evaluating LLM Reasoning through Live Computer Games","created":"2024-12-09","cited_by_count":32,"area":"lr"},{"id":"2502.16906","title":"AutoLogi: Automated Generation of Logic Puzzles for Evaluating Reasoning Abilities of Large Language Models","created":"2025-02-24","cited_by_count":31,"area":"lr"},{"id":"2502.11355","title":"Nuclear Deployed: Analyzing Catastrophic Risks in Decision-making of Autonomous LLM Agents","created":"2025-02-17","cited_by_count":27,"area":"lr"},{"id":"2503.04149","title":"Dynamic Benchmarking of Reasoning Capabilities in Code Large Language Models Under Data Contamination","created":"2025-03-06","cited_by_count":23,"area":"lr"},{"id":"2509.26062","title":"DyFlow: Dynamic Workflow Framework for Agentic Reasoning","created":"2025-09-30","cited_by_count":23,"area":"lr"},{"id":"2602.06176","title":"Large Language Model Reasoning Failures","created":"2026-02-05","cited_by_count":21,"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":"2410.04698","title":"MathHay: An Automated Benchmark for Long-Context Mathematical Reasoning in LLMs","created":"2024-10-07","cited_by_count":13,"area":"lr"},{"id":"2504.06564","title":"Thinking Out Loud: Do Reasoning Models Know When They're Right?","created":"2025-04-09","cited_by_count":12,"area":"lr"},{"id":"2508.10026","title":"SABER: Switchable and Balanced Training for Efficient LLM Reasoning","created":"2025-08-08","cited_by_count":12,"area":"lr"},{"id":"2504.19093","title":"CipherBank: Exploring the Boundary of LLM Reasoning Capabilities through Cryptography Challenges","created":"2025-04-27","cited_by_count":11,"area":"lr"},{"id":"2601.13572","title":"Behavior Knowledge Merge in Reinforced Agentic Models","created":"2026-01-20","cited_by_count":11,"area":"lr"},{"id":"2509.24494","title":"Why Tree-Style Branching Matters for Thought Advantage Estimation in GRPO","created":"2025-09-29","cited_by_count":10,"area":"lr"},{"id":"2507.12885","title":"VAR-MATH: Probing True Mathematical Reasoning in LLMS via Symbolic Multi-Instance Benchmarks","created":"2025-07-17","cited_by_count":8,"area":"lr"},{"id":"2601.15279","title":"MolecularIQ: Characterizing Chemical Reasoning Capabilities Through Symbolic Verification on Molecular Graphs","created":"2026-01-21","cited_by_count":8,"area":"lr"},{"id":"2502.13119","title":"STEER-ME: Assessing the Microeconomic Reasoning of Large Language Models","created":"2025-02-18","cited_by_count":7,"area":"lr"},{"id":"2602.09443","title":"P1-VL: Bridging Visual Perception and Scientific Reasoning in Physics Olympiads","created":"2026-02-10","cited_by_count":7,"area":"lr"},{"id":"2504.02810","title":"Generative Evaluation of Complex Reasoning in Large Language Models","created":"2025-04-03","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":"2605.07579","title":"Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States","created":"2026-05-08","cited_by_count":5,"area":"lr"},{"id":"2506.13065","title":"MotiveBench: How Far Are We From Human-Like Motivational Reasoning in Large Language Models?","created":"2025-06-16","cited_by_count":4,"area":"lr"},{"id":"2601.05073","title":"Milestones over Outcome: Unlocking Geometric Reasoning with Sub-Goal Verifiable Reward","created":"2026-01-08","cited_by_count":4,"area":"lr"},{"id":"2512.21231","title":"MiST: Understanding the Role of Mid-Stage Scientific Training in Developing Chemical Reasoning Models","created":"2025-12-24","cited_by_count":3,"area":"lr"},{"id":"2602.06319","title":"Exposing Weaknesses of Large Reasoning Models through Graph Algorithm Problems","created":"2026-02-06","cited_by_count":3,"area":"lr"},{"id":"2412.15177","title":"Critical-Questions-of-Thought: Steering LLM reasoning with Argumentative Querying","created":"2024-12-19","cited_by_count":2,"area":"lr"},{"id":"2510.14913","title":"Budget-aware Test-time Scaling via Discriminative Verification","created":"2025-10-16","cited_by_count":2,"area":"lr"},{"id":"2508.19035","title":"Investigating Advanced Reasoning of Large Language Models via Black-Box Environment Interaction","created":"2025-08-26","cited_by_count":1,"area":"lr"},{"id":"2510.02306","title":"Drawing Conclusions from Draws: Rethinking Preference Semantics in Arena-Style LLM Evaluation","created":"2025-10-02","cited_by_count":1,"area":"lr"},{"id":"2510.03349","title":"AgentCaster: Reasoning-Guided Tornado Forecasting","created":"2025-10-02","cited_by_count":1,"area":"lr"},{"id":"2510.09970","title":"Follow My Lead: Logical Fallacy Classification with Knowledge-Augmented LLMs","created":"2025-10-11","cited_by_count":1,"area":"lr"},{"id":"2510.22340","title":"DynaSolidGeo: A Dynamic Benchmark for Genuine Spatial Mathematical Reasoning of VLMs in Solid Geometry","created":"2025-10-25","cited_by_count":1,"area":"lr"},{"id":"2511.15886","title":"What Really Counts? Examining Step and Token Level Attribution in Multilingual CoT Reasoning","created":"2025-11-19","cited_by_count":1,"area":"lr"},{"id":"2601.04996","title":"AlgBench: To What Extent Do Large Reasoning Models Understand Algorithms?","created":"2026-01-08","cited_by_count":1,"area":"lr"},{"id":"2603.11082","title":"Quality-Driven Agentic Reasoning for LLM-Assisted Software Design: Questions-of-Thoughts (QoT) as a Time-Series Self-QA Chain","created":"2026-03-10","cited_by_count":1,"area":"lr"},{"id":"2603.19252","title":"GeoChallenge: A Multi-Answer Multiple-Choice Benchmark for Geometric Reasoning with Diagrams","created":"2026-02-25","cited_by_count":1,"area":"lr"},{"id":"2605.01939","title":"StressEval: Failure-Driven Dynamic Benchmarking for Knowledge-Intensive Reasoning in Large Language Models","created":"2026-05-03","cited_by_count":1,"area":"lr"},{"id":"2605.26872","title":"When the Strongest Teacher Is Not the Best Teacher: Student-Centric Answer Selection","created":"2026-05-26","cited_by_count":1,"area":"lr"},{"id":"2605.30898","title":"UniScale: Adaptive Unified Inference Scaling via Online Joint Optimization of Model Routing and Test-Time Scaling","created":"2026-05-29","cited_by_count":1,"area":"lr"},{"id":"2606.02113","title":"A Primer in Post-Training Reasoning Data: What We Know About How It Works","created":"2026-06-01","cited_by_count":1,"area":"lr"},{"id":"2606.27378","title":"Formalizing Latent Thoughts: Four Axioms of Thought Representation in LLMs","created":"2026-05-07","cited_by_count":1,"area":"lr"},{"id":"2508.08933","title":"Reveal-Bangla: A Dataset for Cross-Lingual Multi-Step Reasoning Evaluation","created":"2025-08-12","cited_by_count":0,"area":"lr"},{"id":"2510.05746","title":"ARM: Discovering Agentic Reasoning Modules for Generalizable Multi-Agent Systems","created":"2025-10-07","cited_by_count":0,"area":"lr"},{"id":"2603.05290","title":"X-RAY: Mapping LLM Reasoning Capability via Formalized and Calibrated Probes","created":"2026-03-05","cited_by_count":0,"area":"lr"},{"id":"2605.08498","title":"MathConstraint: Automated Generation of Verified Combinatorial Reasoning Instances for LLMs","created":"2026-05-08","cited_by_count":0,"area":"lr"},{"id":"2605.09900","title":"The Gordian Knot for VLMs: Diagrammatic Knot Reasoning as a Hard Benchmark","created":"2026-05-11","cited_by_count":0,"area":"lr"},{"id":"2605.30391","title":"Social Reasoning in Machines: Investigating Collective Truth-Seeking Dynamics in Large Language Model Debate","created":"2026-05-28","cited_by_count":0,"area":"lr"},{"id":"2607.12733","title":"LLMs Can See the Smoke but not the Fire: Evaluating Abductive Reasoning with Elenchos","created":"2026-07-14","cited_by_count":0,"area":"lr"},{"id":"2608.18242","title":"ClosureBench: A Constructive Benchmark for Compositional Graph Reasoning","created":"2026-08-18","cited_by_count":0,"area":"lr"},{"id":"2608.18921","title":"SMTrap: Cost-Effective DoS Attacks Against Large Reasoning Models via SMT Conflict Guidance","created":"2026-08-19","cited_by_count":0,"area":"lr"},{"id":"2608.21871","title":"The Chase Is the Curriculum, the Capture Anchors the Credit: Pursuit-Evasion Self-Play for Zero-Data LLM Reasoning","created":"2026-08-22","cited_by_count":0,"area":"lr"},{"id":"2609.32470","title":"On the Pitfalls of Verbalized Confidence Priors for Calibrating Large Reasoning Models","created":"2026-09-26","cited_by_count":0,"area":"lr"},{"id":"2609.38409","title":"ArgGYM: A Procedural, Engine-Verified Benchmark for Structured Defeasible Reasoning","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2610.01548","title":"Range-GRPO: Policy Optimization via Pairwise Relations among Reward Intervals","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.16133","title":"Query Your Way Out: Benchmarking Multi-Turn Knowledge Reasoning through Generalized Puzzle Solving","created":"2026-10-12","cited_by_count":0,"area":"lr"},{"id":"2610.19176","title":"Learning from Self-Generated Responses: Reliability--Uncertainty Self-Distillation for Reasoning","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}