{"total":109,"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":"2503.24235","title":"A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?","created":"2025-03-31","cited_by_count":223,"area":"lr"},{"id":"2504.09037","title":"A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems","created":"2025-04-12","cited_by_count":111,"area":"lr"},{"id":"2511.20639","title":"Latent Collaboration in Multi-Agent Systems","created":"2025-11-25","cited_by_count":73,"area":"lr"},{"id":"2509.05396","title":"Talk Isn't Always Cheap: Understanding Failure Modes in Multi-Agent Debate","created":"2025-09-05","cited_by_count":66,"area":"lr"},{"id":"2504.15466","title":"Learning Adaptive Parallel Reasoning with Language Models","created":"2025-04-21","cited_by_count":58,"area":"lr"},{"id":"2502.00674","title":"Rethinking Mixture-of-Agents: Is Mixing Different Large Language Models Beneficial?","created":"2025-02-02","cited_by_count":54,"area":"lr"},{"id":"2502.04780","title":"SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning","created":"2025-02-07","cited_by_count":44,"area":"lr"},{"id":"2505.11484","title":"SoftCoT++: Test-Time Scaling with Soft Chain-of-Thought Reasoning","created":"2025-05-16","cited_by_count":41,"area":"lr"},{"id":"2412.15797","title":"Ensembling Large Language Models with Process Reward-Guided Tree Search for Better Complex Reasoning","created":"2024-12-20","cited_by_count":40,"area":"lr"},{"id":"2501.02497","title":"A Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoning","created":"2025-01-05","cited_by_count":40,"area":"lr"},{"id":"2505.19683","title":"Large Language Models for Planning: A Comprehensive and Systematic Survey","created":"2025-05-26","cited_by_count":40,"area":"lr"},{"id":"2506.21656","title":"Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMs","created":"2025-06-26","cited_by_count":32,"area":"lr"},{"id":"2503.02390","title":"ReSo: A Reward-driven Self-organizing LLM-based Multi-Agent System for Reasoning Tasks","created":"2025-03-04","cited_by_count":31,"area":"lr"},{"id":"2406.11698","title":"Meta Reasoning for Large Language Models","created":"2024-06-17","cited_by_count":29,"area":"lr"},{"id":"2510.11062","title":"Stronger-MAS: Multi-Agent Reinforcement Learning for Collaborative LLMs","created":"2025-10-13","cited_by_count":28,"area":"lr"},{"id":"2411.19477","title":"Provable Scaling Laws for the Test-Time Compute of Large Language Models","created":"2024-11-29","cited_by_count":26,"area":"lr"},{"id":"2510.01499","title":"Beyond Majority Voting: LLM Aggregation by Leveraging Higher-Order Information","created":"2025-10-01","cited_by_count":26,"area":"lr"},{"id":"2410.03524","title":"Steering Large Language Models between Code Execution and Textual Reasoning","created":"2024-10-04","cited_by_count":24,"area":"lr"},{"id":"2503.05641","title":"Skill-Based Mixture-of-Experts: Adaptive Routing for Heterogeneous Reasoning via Inferred Skills","created":"2025-03-07","cited_by_count":24,"area":"lr"},{"id":"2505.11107","title":"Group Think: Multiple Concurrent Reasoning Agents Collaborating at Token Level Granularity","created":"2025-05-16","cited_by_count":22,"area":"lr"},{"id":"2601.12307","title":"Rethinking the Value of Multi-Agent Workflow: A Strong Single Agent Baseline","created":"2026-01-18","cited_by_count":22,"area":"lr"},{"id":"2502.15964","title":"Minions: Cost-efficient Collaboration Between On-device and Cloud Language Models","created":"2025-02-21","cited_by_count":20,"area":"lr"},{"id":"2504.00762","title":"Do We Truly Need So Many Samples? Multi-LLM Repeated Sampling Efficiently Scales Test-Time Compute","created":"2025-04-01","cited_by_count":20,"area":"lr"},{"id":"2505.11556","title":"Systematic Failures in Collective Reasoning under Distributed Information in Multi-Agent LLMs","created":"2025-05-15","cited_by_count":19,"area":"lr"},{"id":"2504.14047","title":"Rethinking Inference-Time Scaling: Efficiency Limits and Linguistic Signals","created":"2025-04-18","cited_by_count":18,"area":"lr"},{"id":"2503.22732","title":"Reasoning Beyond Limits: Advances and Open Problems for LLMs","created":"2025-03-26","cited_by_count":16,"area":"lr"},{"id":"2505.07787","title":"Learning from Peers in Reasoning Models","created":"2025-05-12","cited_by_count":16,"area":"lr"},{"id":"2505.21668","title":"R1-Code-Interpreter: LLMs Reason with Code via Supervised and Multi-stage Reinforcement Learning","created":"2025-05-27","cited_by_count":15,"area":"lr"},{"id":"2510.01279","title":"TUMIX: Multi-Agent Test-Time Scaling with Tool-Use Mixture","created":"2025-09-30","cited_by_count":15,"area":"lr"},{"id":"2512.01992","title":"LLM CHESS: Benchmarking Reasoning and Instruction-Following in LLMs through Chess","created":"2025-12-01","cited_by_count":15,"area":"lr"},{"id":"2505.24273","title":"How Much Backtracking is Enough? Exploring the Interplay of SFT and RL in Enhancing LLM Reasoning","created":"2025-05-30","cited_by_count":13,"area":"lr"},{"id":"2409.07355","title":"Think Together and Work Better: Combining Humans' and LLMs' Think-Aloud Outcomes for Effective Text Evaluation","created":"2024-09-11","cited_by_count":12,"area":"lr"},{"id":"2501.11877","title":"From Drafts to Answers: Unlocking LLM Potential via Aggregation Fine-Tuning","created":"2025-01-21","cited_by_count":12,"area":"lr"},{"id":"2502.20592","title":"Multi2: Multi-Agent Test-Time Scalable Framework for Multi-Document Processing","created":"2025-02-27","cited_by_count":12,"area":"lr"},{"id":"2507.08960","title":"How to Train a Leader: Hierarchical Reasoning in Multi-Agent LLMs","created":"2025-07-11","cited_by_count":12,"area":"lr"},{"id":"2502.04350","title":"CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance","created":"2025-02-04","cited_by_count":11,"area":"lr"},{"id":"2509.07604","title":"K2-Think: A Parameter-Efficient Reasoning System","created":"2025-09-09","cited_by_count":11,"area":"lr"},{"id":"2502.18873","title":"Multi-LLM Collaborative Search for Complex Problem Solving","created":"2025-02-26","cited_by_count":10,"area":"lr"},{"id":"2506.05745","title":"SPRINT: Enabling Interleaved Planning and Parallelized Execution in Reasoning Models","created":"2025-06-06","cited_by_count":10,"area":"lr"},{"id":"2507.00711","title":"Large Reasoning Models are not thinking straight: on the unreliability of thinking trajectories","created":"2025-07-01","cited_by_count":10,"area":"lr"},{"id":"2409.07123","title":"Cross-Refine: Improving Natural Language Explanation Generation by Learning in Tandem","created":"2024-09-11","cited_by_count":9,"area":"lr"},{"id":"2503.23219","title":"Aurelia: Test-time Reasoning Distillation in Audio-Visual LLMs","created":"2025-03-29","cited_by_count":9,"area":"lr"},{"id":"2505.19634","title":"Faster and Better LLMs via Latency-Aware Test-Time Scaling","created":"2025-05-26","cited_by_count":9,"area":"lr"},{"id":"2506.04611","title":"Revisiting Test-Time Scaling: A Survey and a Diversity-Aware Method for Efficient Reasoning","created":"2025-06-05","cited_by_count":9,"area":"lr"},{"id":"2507.20187","title":"Diversity-Enhanced Reasoning for Subjective Questions","created":"2025-07-27","cited_by_count":9,"area":"lr"},{"id":"2509.24771","title":"LatentEvolve: Self-Evolving Test-Time Scaling in Latent Space","created":"2025-09-29","cited_by_count":9,"area":"lr"},{"id":"2511.06727","title":"S-DAG: A Subject-Based Directed Acyclic Graph for Multi-Agent Heterogeneous Reasoning","created":"2025-11-10","cited_by_count":9,"area":"lr"},{"id":"2512.05105","title":"Semantic Soft Bootstrapping: Long Context Reasoning in LLMs without Reinforcement Learning","created":"2025-12-04","cited_by_count":9,"area":"lr"},{"id":"2602.15382","title":"The Vision Wormhole: Latent-Space Communication in Heterogeneous Multi-Agent Systems","created":"2026-02-17","cited_by_count":9,"area":"lr"},{"id":"2505.07313","title":"Towards Multi-Agent Reasoning Systems for Collaborative Expertise Delegation: An Exploratory Design Study","created":"2025-05-12","cited_by_count":8,"area":"lr"},{"id":"2511.07396","title":"C3PO: Optimized Large Language Model Cascades with Probabilistic Cost Constraints for Reasoning","created":"2025-11-10","cited_by_count":8,"area":"lr"},{"id":"2510.13903","title":"Benefits and Limitations of Communication in Multi-Agent Reasoning","created":"2025-10-14","cited_by_count":7,"area":"lr"},{"id":"2502.09955","title":"Diverse Inference and Verification for Advanced Reasoning","created":"2025-02-14","cited_by_count":6,"area":"lr"},{"id":"2506.17113","title":"MEXA: Towards General Multimodal Reasoning with Dynamic Multi-Expert Aggregation","created":"2025-06-20","cited_by_count":6,"area":"lr"},{"id":"2510.05077","title":"Slm-mux: Orchestrating small language models for reasoning","created":"2025-10-06","cited_by_count":6,"area":"lr"},{"id":"2507.16809","title":"LingBench++: A Linguistically-Informed Benchmark and Reasoning Framework for Multi-Step and Cross-Cultural Inference with LLMs","created":"2025-07-22","cited_by_count":5,"area":"lr"},{"id":"2510.10047","title":"SwarmSys: Decentralized Swarm-Inspired Agents for Scalable and Adaptive Reasoning","created":"2025-10-11","cited_by_count":5,"area":"lr"},{"id":"2607.17384","title":"Quantifying Diversity of Thought: A Predictive Law of Weighted LLM Ensemble Lift","created":"2026-07-19","cited_by_count":5,"area":"lr"},{"id":"2507.02851","title":"MOTIF: Modular Thinking via Reinforcement Fine-tuning in LLMs","created":"2025-07-03","cited_by_count":4,"area":"lr"},{"id":"2602.04288","title":"Contextual Drag: How Errors in the Context Affect LLM Reasoning","created":"2026-02-04","cited_by_count":4,"area":"lr"},{"id":"2409.11783","title":"Development and bilingual evaluation of Japanese medical large language model within reasonably low computational resources","created":"2024-09-18","cited_by_count":3,"area":"lr"},{"id":"2508.03333","title":"CTTS: Collective Test-Time Scaling","created":"2025-08-05","cited_by_count":3,"area":"lr"},{"id":"2605.01566","title":"Multi-Agent Reasoning Improves Compute Efficiency: Pareto-Optimal Test-Time Scaling","created":"2026-05-02","cited_by_count":3,"area":"lr"},{"id":"2606.23595","title":"SPIRAL: Learning to Search and Aggregate","created":"2026-06-22","cited_by_count":3,"area":"lr"},{"id":"2502.19622","title":"Weaker LLMs' Opinions Also Matter: Mixture of Opinions Enhances LLM's Mathematical Reasoning","created":"2025-02-26","cited_by_count":2,"area":"lr"},{"id":"2508.21762","title":"Reasoning-Intensive Regression","created":"2025-08-29","cited_by_count":2,"area":"lr"},{"id":"2510.04488","title":"Multi-Agent Collaborative Intelligence: Dual-Dial Control for Reliable LLM Reasoning","created":"2025-10-06","cited_by_count":2,"area":"lr"},{"id":"2603.24481","title":"Multi-Agent Reasoning with Consistency Verification Improves Uncertainty Calibration in Medical MCQA","created":"2026-03-25","cited_by_count":2,"area":"lr"},{"id":"2605.14163","title":"Agentic Systems as Boosting Weak Reasoning Models","created":"2026-05-13","cited_by_count":2,"area":"lr"},{"id":"2607.10139","title":"LLMs as a Jury: Cross-Model Consensus Can Outperform Process Reward Models for LLM Reasoning","created":"2026-07-11","cited_by_count":2,"area":"lr"},{"id":"2607.27783","title":"Reasoning Consensus: Structural Ensembling of LLM Reasoning via Weighted DAG Aggregation","created":"2026-07-30","cited_by_count":2,"area":"lr"},{"id":"2511.22242","title":"Rethinking Test Time Scaling for Flow-Matching Generative Models","created":"2025-11-27","cited_by_count":1,"area":"lr"},{"id":"2511.22854","title":"CRAwDAD: Causal Reasoning Augmentation with Dual-Agent Debate","created":"2025-11-28","cited_by_count":1,"area":"lr"},{"id":"2601.13992","title":"\"The Whole Is Greater Than the Sum of Its Parts\": A Compatibility-Aware Multi-Teacher CoT Distillation Framework","created":"2026-01-20","cited_by_count":1,"area":"lr"},{"id":"2601.21533","title":"ARGORA: Orchestrated Argumentation for Causally Grounded LLM Reasoning and Decision Making","created":"2026-01-29","cited_by_count":1,"area":"lr"},{"id":"2603.13256","title":"Training-Free Agentic AI: Probabilistic Control and Coordination in Multi-Agent LLM Systems","created":"2026-02-24","cited_by_count":1,"area":"lr"},{"id":"2605.07646","title":"MAVEN: Multi-Agent Verification-Elaboration Network with In-Step Epistemic Auditing","created":"2026-05-08","cited_by_count":1,"area":"lr"},{"id":"2605.19418","title":"Conflict-Resilient Multi-Agent Reasoning via Signed Graph Modeling","created":"2026-05-19","cited_by_count":1,"area":"lr"},{"id":"2605.22897","title":"From Residuals to Reasons: LLM-Guided Mechanism Inference from Tabular Data","created":"2026-05-21","cited_by_count":1,"area":"lr"},{"id":"2605.25188","title":"DarkForest: Less Talk, Higher Accuracy for Multi-Agent LLMs","created":"2026-05-24","cited_by_count":1,"area":"lr"},{"id":"2606.08728","title":"Artificial Intelligence for Mathematical Reasoning: An Integrated Survey of Language Models, Neuro-symbolic Systems, and Verified Discovery","created":"2026-06-07","cited_by_count":1,"area":"lr"},{"id":"2606.27268","title":"E-TTS: A New Embodied Test-Time Scaling Framework for Robotic Manipulation","created":"2026-06-25","cited_by_count":1,"area":"lr"},{"id":"2609.10996","title":"Rethinking Verbalized Confidence for LLM-as-a-Judge: A Compatibility Shift on Post-2025 Proprietary Models","created":"2026-09-10","cited_by_count":1,"area":"lr"},{"id":"2407.12877","title":"ReFeR: Improving Evaluation and Reasoning through Hierarchy of Models","created":"2024-07-16","cited_by_count":0,"area":"lr"},{"id":"2412.07779","title":"Evolution of Thought: Diverse and High-Quality Reasoning via Multi-Objective Optimization","created":"2024-11-24","cited_by_count":0,"area":"lr"},{"id":"2509.19762","title":"The Conductor and the Engine: A Path Towards Co-Designed Reasoning","created":"2025-09-24","cited_by_count":0,"area":"lr"},{"id":"2509.23730","title":"EAPO: Enhancing Policy Optimization with On-Demand Expert Assistance","created":"2025-09-28","cited_by_count":0,"area":"lr"},{"id":"2510.14353","title":"CURE: Confidence-driven Unified Reasoning Ensemble Framework for Medical Question Answering","created":"2025-10-16","cited_by_count":0,"area":"lr"},{"id":"2602.09173","title":"$n$-Musketeers: Reinforcement Learning Shapes Collaboration Among Language Models","created":"2026-02-09","cited_by_count":0,"area":"lr"},{"id":"2603.17822","title":"Multi-Source Evidence Fusion for Audio Question Answering","created":"2026-03-18","cited_by_count":0,"area":"lr"},{"id":"2604.17450","title":"Compiling Deterministic Structure into SLM Harnesses","created":"2026-04-19","cited_by_count":0,"area":"lr"},{"id":"2604.21190","title":"SpatiO: Adaptive Test-Time Orchestration of Vision-Language Agents for Spatial Reasoning","created":"2026-04-23","cited_by_count":0,"area":"lr"},{"id":"2605.02290","title":"Distilling Long-CoT Reasoning through Collaborative Step-wise Multi-Teacher Decoding","created":"2026-05-04","cited_by_count":0,"area":"lr"},{"id":"2605.08704","title":"AgentPSO: Evolving Agent Reasoning Skill via Multi-agent Particle Swarm Optimization","created":"2026-05-09","cited_by_count":0,"area":"lr"},{"id":"2606.05158","title":"Streaming Communication in Multi-Agent Reasoning","created":"2026-06-03","cited_by_count":0,"area":"lr"},{"id":"2606.06941","title":"Quantum-Inspired Trace-Augmented Evidence Selection for Reasoning over Structured Hypothesis Spaces","created":"2026-06-05","cited_by_count":0,"area":"lr"},{"id":"2607.01661","title":"Diverse Evidence, Better Forecasts: Multi-Agent Deliberation Under Information Asymmetry","created":"2026-07-02","cited_by_count":0,"area":"lr"},{"id":"2607.23678","title":"Focus Is All You Need: Adaptive Goal-aware Attention Orchestration for Multi-Agent Graph Systems","created":"2026-07-26","cited_by_count":0,"area":"lr"},{"id":"2608.24001","title":"Diverse by Reasoning: Harnessing the Wisdom of LLM Crowds for Future Prediction","created":"2026-08-25","cited_by_count":0,"area":"lr"}],"next_cursor":"100"}