{"total":63,"rows":[{"id":"2503.09567","title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","created":"2025-03-12","cited_by_count":384,"area":"lr"},{"id":"2503.19877","title":"Scaling Evaluation-time Compute with Reasoning Models as Evaluators","created":"2025-03-25","cited_by_count":13,"area":"lr"},{"id":"2507.12948","title":"Probabilistic Soundness Guarantees in LLM Reasoning Chains","created":"2025-07-17","cited_by_count":13,"area":"lr"},{"id":"2602.03955","title":"AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent","created":"2026-02-03","cited_by_count":13,"area":"lr"},{"id":"2506.02532","title":"ReasoningFlow: Semantic Structure of Complex Reasoning Traces","created":"2025-06-03","cited_by_count":12,"area":"lr"},{"id":"2511.10788","title":"From Efficiency to Adaptivity: A Deeper Look at Adaptive Reasoning in Large Language Models","created":"2025-11-13","cited_by_count":12,"area":"lr"},{"id":"2509.16584","title":"From Scores to Steps: Diagnosing and Improving LLM Performance in Evidence-Based Medical Calculations","created":"2025-09-20","cited_by_count":11,"area":null},{"id":"2510.20603","title":"What Defines Good Reasoning in LLMs? Dissecting Reasoning Steps with Multi-Aspect Evaluation","created":"2025-10-23","cited_by_count":10,"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":"2510.08847","title":"What Is Your Agent's GPA? A Framework for Evaluating Agent Goal-Plan-Action Alignment","created":"2025-10-09","cited_by_count":8,"area":"agents"},{"id":"2506.05243","title":"CLATTER: Comprehensive Entailment Reasoning for Hallucination Detection","created":"2025-06-05","cited_by_count":7,"area":"lr"},{"id":"2510.10973","title":"Chart-RVR: Reinforcement Learning with Verifiable Rewards for Explainable Chart Reasoning","created":"2025-10-13","cited_by_count":7,"area":"lr"},{"id":"2507.02145","title":"Reasoning or Not? A Comprehensive Evaluation of Reasoning LLMs for Dialogue Summarization","created":"2025-07-02","cited_by_count":6,"area":"lr"},{"id":"2508.16599","title":"Humans Perceive Wrong Narratives from AI Reasoning Texts","created":"2025-08-09","cited_by_count":6,"area":null},{"id":"2512.23511","title":"Beyond Correctness: Exposing LLM-generated Logical Flaws in Reasoning via Multi-step Automated Theorem Proving","created":"2025-12-29","cited_by_count":6,"area":"lr"},{"id":"2508.08386","title":"CoDAE: Adapting Large Language Models for Education via Chain-of-Thought Data Augmentation","created":"2025-08-11","cited_by_count":5,"area":"lr"},{"id":"2509.18163","title":"Thinking in a Crowd: How Auxiliary Information Shapes LLM Reasoning","created":"2025-09-17","cited_by_count":5,"area":"lr"},{"id":"2512.01020","title":"Evaluating Legal Reasoning Traces with Legal Issue Tree Rubrics","created":"2025-11-30","cited_by_count":5,"area":"lr"},{"id":"2602.08498","title":"Characterizing, Evaluating, and Optimizing Complex Reasoning","created":"2026-02-09","cited_by_count":5,"area":"lr"},{"id":"2603.20508","title":"Measuring Weak-to-Strong Legibility of Reasoning Models","created":"2026-03-20","cited_by_count":5,"area":"lr"},{"id":"2605.21127","title":"Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning","created":"2026-05-20","cited_by_count":4,"area":"lr"},{"id":"2511.04070","title":"T-FIX: Text-Based Explanations with Features Interpretable to eXperts","created":"2025-11-06","cited_by_count":2,"area":null},{"id":"2511.05874","title":"An Empirical Study of Reasoning Steps in Thinking Code LLMs","created":"2025-11-08","cited_by_count":2,"area":"lr"},{"id":"2512.12576","title":"Coupled Variational Reinforcement Learning for Language Model General Reasoning","created":"2025-12-14","cited_by_count":2,"area":"lr"},{"id":"2602.09805","title":"Beyond Accuracy: Decomposing the Reasoning Efficiency of LLMs","created":"2026-02-10","cited_by_count":2,"area":"lr"},{"id":"2604.06695","title":"Reasoning Fails Where Step Flow Breaks","created":"2026-04-08","cited_by_count":2,"area":"lr"},{"id":"2607.11175","title":"The Path to Self-Evolving Clinical Systems: Scaling Medical Agents from Assistance to Autonomy","created":"2026-07-13","cited_by_count":2,"area":"mllm"},{"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":"2511.02627","title":"DecompSR: A dataset for decomposed analyses of compositional multihop spatial reasoning","created":"2025-11-04","cited_by_count":1,"area":"lr"},{"id":"2512.16750","title":"Plausibility as Failure: How LLMs and Humans Co-Construct Epistemic Error","created":"2025-12-18","cited_by_count":1,"area":null},{"id":"2601.10649","title":"MINERVA-Cultural: A Benchmark for Cultural and Multilingual Long Video Reasoning","created":"2026-01-15","cited_by_count":1,"area":"lr"},{"id":"2601.10775","title":"LLMs for Game Theory: Entropy-Guided In-Context Learning and Adaptive CoT Reasoning","created":"2026-01-15","cited_by_count":1,"area":"lr"},{"id":"2602.11516","title":"Human-Inspired Continuous Learning of Internal Reasoning Processes: Learning How to Think for Adaptive AI Systems","created":"2026-02-12","cited_by_count":1,"area":"lr"},{"id":"2602.15332","title":"Directional Reasoning Trajectory Change (DRTC): Identifying Critical Trace Segments in Reasoning Models","created":"2026-02-17","cited_by_count":1,"area":"lr"},{"id":"2602.21143","title":"A Benchmark for Deep Information Synthesis","created":"2026-02-24","cited_by_count":1,"area":null},{"id":"2603.01025","title":"One-Token Verification for Reasoning Correctness Estimation","created":"2026-03-01","cited_by_count":1,"area":"lr"},{"id":"2603.02266","title":"When Scaling Fails: Mitigating Audio Perception Decay of LALMs via Multi-Step Perception-Aware Reasoning","created":"2026-02-28","cited_by_count":1,"area":"lr"},{"id":"2604.08723","title":"Decomposing the Delta: What Do Models Actually Learn from Preference Pairs?","created":"2026-04-09","cited_by_count":1,"area":"alignment"},{"id":"2605.15574","title":"MI-CXR: A Benchmark for Longitudinal Reasoning over Multi-Interval Chest X-rays","created":"2026-05-15","cited_by_count":1,"area":"lr"},{"id":"2605.20548","title":"What Do Agents Communicate? Characterizing Information Exchange in Multi-Agent Systems","created":"2026-05-19","cited_by_count":1,"area":"agents"},{"id":"2606.16545","title":"Can LLM Coding Agents Reason About Time Series?","created":"2026-06-15","cited_by_count":1,"area":"lr"},{"id":"2608.00764","title":"FinDeepIndicator: Benchmarking Deep Research Agents in End-to-End Financial Indicator Construction","created":"2026-08-01","cited_by_count":1,"area":"agents"},{"id":"2609.29508","title":"Evaluation of Multi-Turn Consistency in LLM Agents: Survival Analysis and Failure-Rationale Taxonomy","created":"2026-08-26","cited_by_count":1,"area":"agents"},{"id":"2505.20707","title":"Dissecting Physics Reasoning in Small Language Models: A Multi-Dimensional Analysis from an Educational Perspective","created":"2025-05-27","cited_by_count":0,"area":"lr"},{"id":"2509.20105","title":"PEPS: Quantum-Inspired Reinforcement Learning for Coherent Reasoning Traces in LLMs","created":"2025-09-24","cited_by_count":0,"area":"lr"},{"id":"2512.04254","title":"Hey GPT-OSS, Looks Like You Got It -- Now Walk Me Through It! An Assessment of the Reasoning Language Models Chain of Thought Mechanism for Digital Forensics","created":"2025-12-03","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":"2601.07430","title":"KALE: Enhancing Knowledge Manipulation in Large Language Models via Knowledge-aware Learning","created":"2026-01-12","cited_by_count":0,"area":null},{"id":"2601.11252","title":"Beyond Model Scaling: Test-Time Intervention for Efficient Deep Reasoning","created":"2026-01-16","cited_by_count":0,"area":"lr"},{"id":"2602.02295","title":"EvalQReason: A Framework for Step-Level Reasoning Evaluation in Large Language Models","created":"2026-02-02","cited_by_count":0,"area":"lr"},{"id":"2604.04852","title":"Strengthening Human-Centric Chain-of-Thought Reasoning Integrity in LLMs via a Structured Prompt Framework","created":"2026-04-06","cited_by_count":0,"area":"lr"},{"id":"2604.09890","title":"Should We be Pedantic About Reasoning Errors in Machine Translation?","created":"2026-04-10","cited_by_count":0,"area":"lr"},{"id":"2604.11996","title":"Filtered Reasoning Score: Evaluating Reasoning Quality on a Model's Most-Confident Traces","created":"2026-04-13","cited_by_count":0,"area":"lr"},{"id":"2604.21057","title":"TRACES: Tagging Reasoning Steps for Adaptive Cost-Efficient Early-Stopping","created":"2026-04-22","cited_by_count":0,"area":"lr"},{"id":"2604.21204","title":"On Reasoning Behind Next Occupation Recommendation","created":"2026-04-23","cited_by_count":0,"area":"lr"},{"id":"2605.13290","title":"What properties of reasoning supervision are associated with improved downstream model quality?","created":"2026-05-13","cited_by_count":0,"area":"lr"},{"id":"2606.00683","title":"OCC-RAG: Optimal Cognitive Core for Faithful Question Answering","created":"2026-05-30","cited_by_count":0,"area":"lr"},{"id":"2606.30653","title":"The Consistency Dilemma in LLMs: Generator-Evaluator Agreement and Vulnerability to Mistakes","created":"2026-06-16","cited_by_count":0,"area":"lr"},{"id":"2608.08020","title":"Thought-Level Beam Search for Reasoning","created":"2026-08-08","cited_by_count":0,"area":"lr"},{"id":"2608.22713","title":"A Source-Grounded Framework for Constructing and Evaluating Progressive Multimodal Diagnostic Dialogues from Clinical Case Reports","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.02000","title":"Who Drives the Probability Game of VLMs? A Temporal Causal Drive Evaluation Framework","created":"2026-09-02","cited_by_count":0,"area":"mllm"},{"id":"2609.24071","title":"Monitorable Chart Reasoning Agents via Verifiable Process Rewards","created":"2026-09-21","cited_by_count":0,"area":"lr"},{"id":"2610.19108","title":"Towards a Data-Centric Understanding of Spatial Reasoning in Multimodal Large Language Models","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}