{"total":78,"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":"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":"2503.08569","title":"DeepReview: Improving LLM-based Paper Review with Human-like Deep Thinking Process","created":"2025-03-11","cited_by_count":100,"area":"lr"},{"id":"2510.23595","title":"Multi-Agent Evolve: LLM Self-Improve through Co-evolution","created":"2025-10-27","cited_by_count":60,"area":"lr"},{"id":"2504.10481","title":"xVerify: Efficient Answer Verifier for Reasoning Model Evaluations","created":"2025-04-14","cited_by_count":55,"area":"lr"},{"id":"2508.14029","title":"Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR","created":"2025-08-19","cited_by_count":54,"area":"lr"},{"id":"2506.09942","title":"VerIF: Verification Engineering for Reinforcement Learning in Instruction Following","created":"2025-06-11","cited_by_count":44,"area":"lr"},{"id":"2506.08989","title":"SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM Reasoning","created":"2025-06-10","cited_by_count":42,"area":"lr"},{"id":"2502.06855","title":"Self-Supervised Prompt Optimization","created":"2025-02-07","cited_by_count":37,"area":"lr"},{"id":"2505.13975","title":"DRP: Distilled Reasoning Pruning with Skill-aware Step Decomposition for Efficient Large Reasoning Models","created":"2025-05-20","cited_by_count":30,"area":"lr"},{"id":"2609.26550","title":"JEV-as-a-Judge: Accept When Confident, Escalate When Unsure","created":"2026-09-22","cited_by_count":30,"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":"2504.10337","title":"Heimdall: test-time scaling on the generative verification","created":"2025-04-14","cited_by_count":26,"area":"lr"},{"id":"2504.01995","title":"Brains vs. Bytes: Evaluating LLM Proficiency in Olympiad Mathematics","created":"2025-04-01","cited_by_count":24,"area":"lr"},{"id":"2412.15118","title":"Reasoning Through Execution: Unifying Process and Outcome Rewards for Code Generation","created":"2024-12-19","cited_by_count":21,"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":"2502.12501","title":"Crowd Comparative Reasoning: Unlocking Comprehensive Evaluations for LLM-as-a-Judge","created":"2025-02-18","cited_by_count":19,"area":"lr"},{"id":"2512.03109","title":"E-valuator: Reliable Agent Verifiers with Sequential Hypothesis Testing","created":"2025-12-02","cited_by_count":17,"area":"lr"},{"id":"2507.17849","title":"Dynamic and Generalizable Process Reward Modeling","created":"2025-07-23","cited_by_count":16,"area":"lr"},{"id":"2505.02156","title":"Adaptive Social Learning via Mode Policy Optimization for Language Agents","created":"2025-05-04","cited_by_count":15,"area":"lr"},{"id":"2505.17250","title":"ConciseRL: Conciseness-Guided Reinforcement Learning for Efficient Reasoning Models","created":"2025-05-22","cited_by_count":14,"area":"lr"},{"id":"2505.17406","title":"Robust Answers, Fragile Logic: Probing the Decoupling Hypothesis in LLM Reasoning","created":"2025-05-23","cited_by_count":11,"area":"lr"},{"id":"2504.00406","title":"VerifiAgent: a Unified Verification Agent in Language Model Reasoning","created":"2025-04-01","cited_by_count":10,"area":"lr"},{"id":"2504.02181","title":"A Survey of Scaling in Large Language Model Reasoning","created":"2025-04-02","cited_by_count":10,"area":"lr"},{"id":"2601.21459","title":"HER: Human-like Reasoning and Reinforcement Learning for LLM Role-playing","created":"2026-01-29","cited_by_count":10,"area":"lr"},{"id":"2505.18759","title":"The Quest for Efficient Reasoning: A Data-Centric Benchmark to CoT Distillation","created":"2025-05-24","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":"2502.09183","title":"RefineCoder: Iterative Improving of Large Language Models via Adaptive Critique Refinement for Code Generation","created":"2025-02-13","cited_by_count":8,"area":"lr"},{"id":"2503.01642","title":"Graph-Augmented Reasoning: Evolving Step-by-Step Knowledge Graph Retrieval for LLM Reasoning","created":"2025-03-03","cited_by_count":8,"area":"lr"},{"id":"2504.10187","title":"DeepTrans: Deep Reasoning Translation via Reinforcement Learning","created":"2025-04-14","cited_by_count":8,"area":"lr"},{"id":"2604.11741","title":"Collaborative Multi-Agent Scripts Generation for Enhancing Imperfect-Information Reasoning in Murder Mystery Games","created":"2026-04-13","cited_by_count":6,"area":"lr"},{"id":"2503.15944","title":"From Chaos to Order: The Atomic Reasoner Framework for Fine-grained Reasoning in Large Language Models","created":"2025-03-20","cited_by_count":5,"area":"lr"},{"id":"2504.08120","title":"DeepSeek-R1 vs. o3-mini: How Well can Reasoning LLMs Evaluate MT and Summarization?","created":"2025-04-10","cited_by_count":5,"area":"lr"},{"id":"2505.11875","title":"J1: Exploring Simple Test-Time Scaling for LLM-as-a-Judge","created":"2025-05-17","cited_by_count":5,"area":"lr"},{"id":"2508.19813","title":"T2R-bench: A Benchmark for Generating Article-Level Reports from Real World Industrial Tables","created":"2025-08-27","cited_by_count":5,"area":"lr"},{"id":"2509.15739","title":"Can LLMs Judge Debates? Evaluating Non-Linear Reasoning via Argumentation Theory Semantics","created":"2025-09-19","cited_by_count":5,"area":"lr"},{"id":"2601.16130","title":"Replicating Human Motivated Reasoning Studies with LLMs","created":"2026-01-22","cited_by_count":5,"area":"lr"},{"id":"2502.19409","title":"ImageChain: Advancing Sequential Image-to-Text Reasoning in Multimodal Large Language Models","created":"2025-02-26","cited_by_count":4,"area":"lr"},{"id":"2506.05766","title":"BioMol-MQA: A Multi-Modal Question Answering Dataset For LLM Reasoning Over Bio-Molecular Interactions","created":"2025-06-06","cited_by_count":4,"area":"lr"},{"id":"2507.11936","title":"A Survey of Deep Learning for Geometry Problem Solving","created":"2025-07-16","cited_by_count":4,"area":"lr"},{"id":"2510.10930","title":"Evaluating Language Models' Evaluations of Games","created":"2025-10-13","cited_by_count":4,"area":"lr"},{"id":"2511.21005","title":"ICPO: Intrinsic Confidence-Driven Group Relative Preference Optimization for Efficient Reinforcement Learning","created":"2025-11-26","cited_by_count":4,"area":"lr"},{"id":"2512.23213","title":"Scoring, Reasoning, and Selecting the Best! Ensembling Large Language Models via a Peer-Review Process","created":"2025-12-29","cited_by_count":4,"area":"lr"},{"id":"2601.06860","title":"ET-Agent: Incentivizing Effective Tool-Integrated Reasoning Agent via Behavior Calibration","created":"2026-01-11","cited_by_count":4,"area":"lr"},{"id":"2603.20046","title":"Experience is the Best Teacher: Motivating Effective Exploration in Reinforcement Learning for LLMs","created":"2026-03-20","cited_by_count":3,"area":"lr"},{"id":"2606.02578","title":"Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward Modeling","created":"2026-06-01","cited_by_count":3,"area":"lr"},{"id":"2412.15748","title":"Critique of Impure Reason: Unveiling the reasoning behaviour of medical Large Language Models","created":"2024-12-20","cited_by_count":2,"area":"lr"},{"id":"2501.00244","title":"Have We Designed Generalizable Structural Knowledge Promptings? Systematic Evaluation and Rethinking","created":"2024-12-31","cited_by_count":2,"area":"lr"},{"id":"2505.19502","title":"CODE-DITING: A Reasoning-Based Metric for Functional Alignment in Code Evaluation","created":"2025-05-26","cited_by_count":2,"area":"lr"},{"id":"2510.21828","title":"Structured and Abstractive Reasoning on Multi-modal Relational Knowledge Images","created":"2025-10-22","cited_by_count":2,"area":"lr"},{"id":"2601.18730","title":"Reflect: Transparent Principle-Guided Reasoning for Constitutional Alignment at Scale","created":"2026-01-26","cited_by_count":2,"area":"lr"},{"id":"2602.00723","title":"Rethinking Hallucinations: Correctness, Consistency, and Prompt Multiplicity","created":"2026-01-31","cited_by_count":2,"area":"lr"},{"id":"2602.05242","title":"EGSS: Entropy-guided Stepwise Scaling for Reliable Software Engineering","created":"2026-02-05","cited_by_count":2,"area":"lr"},{"id":"2603.20133","title":"Reasoning Gets Harder for LLMs Inside A Dialogue","created":"2026-03-20","cited_by_count":2,"area":"lr"},{"id":"2604.14892","title":"Can LLMs Accurately Score Medical Diagnoses and Clinical Reasoning?","created":"2026-04-16","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":"2504.12334","title":"QM-ToT: A Medical Tree of Thoughts Reasoning Framework for Quantized Model","created":"2025-04-13","cited_by_count":1,"area":"lr"},{"id":"2508.05009","title":"Can Large Language Models Integrate Spatial Data? Empirical Insights into Reasoning Strengths and Computational Weaknesses","created":"2025-08-07","cited_by_count":1,"area":"lr"},{"id":"2601.15050","title":"Beyond Factual Accuracy: Evaluating Global Reasoning Integrity in RAG Systems with LogicScore","created":"2026-01-21","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":"2603.19266","title":"Probing to Refine: Reinforcement Distillation of LLMs via Explanatory Inversion","created":"2026-02-26","cited_by_count":1,"area":"lr"},{"id":"2604.15951","title":"Integrating Graphs, Large Language Models, and Agents: Reasoning and Retrieval","created":"2026-04-17","cited_by_count":1,"area":"lr"},{"id":"2504.12333","title":"Meta-Evaluating Local LLMs: Rethinking Performance Metrics for Serious Games","created":"2025-04-13","cited_by_count":0,"area":"lr"},{"id":"2505.20214","title":"When Slower Isn't Truer: Inverse Scaling Law of Truthfulness in Multimodal Reasoning","created":"2025-05-26","cited_by_count":0,"area":"lr"},{"id":"2506.14371","title":"ELLIS Alicante at CQs-Gen 2025: Winning the critical thinking questions shared task: LLM-based question generation and selection","created":"2025-06-17","cited_by_count":0,"area":"lr"},{"id":"2510.18095","title":"SMaRT: Select, Mix, and ReinvenT -- A Strategy Fusion Framework for LLM-Driven Reasoning and Planning","created":"2025-10-20","cited_by_count":0,"area":"lr"},{"id":"2601.03940","title":"Large-Scale Aspect-Based Sentiment Analysis with Reasoning-Infused LLMs","created":"2026-01-07","cited_by_count":0,"area":"lr"},{"id":"2602.07361","title":"ViHERMES: A Graph-Grounded Multihop Question Answering Benchmark and System for Vietnamese Healthcare Regulations","created":"2026-02-07","cited_by_count":0,"area":"lr"},{"id":"2603.18282","title":"CycleCap: Improving VLMs Captioning Performance via Self-Supervised Cycle Consistency Fine-Tuning","created":"2026-03-18","cited_by_count":0,"area":"lr"},{"id":"2605.05643","title":"Text-Graph Synergy: A Bidirectional Verification and Completion Framework for RAG","created":"2026-05-07","cited_by_count":0,"area":"lr"},{"id":"2606.25552","title":"SFL-MTSC: Leveraging Semantic Frame-Level Multi-Task Self-Consistency for Robust Multi-Intent Spoken Language Understanding","created":"2026-06-24","cited_by_count":0,"area":"lr"},{"id":"2607.07619","title":"Rethinking Code Performance Benchmarks for LLMs","created":"2026-07-08","cited_by_count":0,"area":"lr"},{"id":"2607.08285","title":"Psychological Competence as a Missing Dimension in AI Evaluation","created":"2026-07-09","cited_by_count":0,"area":"lr"},{"id":"2607.20440","title":"Answer-then-Edit: Reasoning Skeleton Editing for Anti-Distillation with Preserved Utility","created":"2026-05-12","cited_by_count":0,"area":"lr"},{"id":"2607.24199","title":"Reasoning to Regulate: Chain-of-Thought for Traffic Rule Understanding","created":"2026-07-27","cited_by_count":0,"area":"lr"},{"id":"2608.21897","title":"From Solver Feedback to Faithful Plans: Multi-Role Reinforcement Learning for Symbolic Planning","created":"2026-08-22","cited_by_count":0,"area":"lr"},{"id":"2609.13158","title":"TestHallVQA: Exploring LVLMs' Document-Level Reasoning under Redundant Contexts from Scientific Exams","created":"2026-07-15","cited_by_count":0,"area":"lr"},{"id":"2610.03136","title":"Investigating the Role of Reasoning-Language Alignment in Monolingual Retrieval-Augmented Generation","created":"2026-10-02","cited_by_count":0,"area":"lr"}],"next_cursor":null}