{"total":237,"rows":[{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708,"area":"lr"},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139,"area":"lr"},{"id":"2203.07814","title":"Competition-Level Code Generation with AlphaCode","created":"2022-02-08","cited_by_count":1462,"area":"lr"},{"id":"2206.14858","title":"Solving Quantitative Reasoning Problems with Language Models","created":"2022-06-29","cited_by_count":1392,"area":"lr"},{"id":"2305.04388","title":"Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting","created":"2023-05-07","cited_by_count":1122,"area":"lr"},{"id":"2504.13837","title":"Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?","created":"2025-04-18","cited_by_count":982,"area":"lr"},{"id":"2307.13702","title":"Measuring Faithfulness in Chain-of-Thought Reasoning","created":"2023-07-17","cited_by_count":703,"area":"lr"},{"id":"2304.06767","title":"RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment","created":"2023-04-13","cited_by_count":686,"area":"lr"},{"id":"2211.10435","title":"PAL: Program-aided Language Models","created":"2022-11-18","cited_by_count":652,"area":"lr"},{"id":"2310.10631","title":"Llemma: An Open Language Model For Mathematics","created":"2023-10-16","cited_by_count":388,"area":"lr"},{"id":"2501.12570","title":"O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning","created":"2025-01-22","cited_by_count":279,"area":"lr"},{"id":"2202.04053","title":"DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models","created":"2022-02-08","cited_by_count":230,"area":"lr"},{"id":"2311.18651","title":"LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning","created":"2023-11-30","cited_by_count":210,"area":"lr"},{"id":"2402.10200","title":"Chain-of-Thought Reasoning Without Prompting","created":"2024-02-15","cited_by_count":210,"area":"lr"},{"id":"2505.19590","title":"Learning to Reason without External Rewards","created":"2025-05-26","cited_by_count":210,"area":"lr"},{"id":"2410.01560","title":"OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data","created":"2024-10-02","cited_by_count":200,"area":"lr"},{"id":"2305.00633","title":"Self-Evaluation Guided Beam Search for Reasoning","created":"2023-05-01","cited_by_count":196,"area":"lr"},{"id":"2505.24864","title":"ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models","created":"2025-05-30","cited_by_count":194,"area":"lr"},{"id":"2503.00307","title":"Remasking Discrete Diffusion Models with Inference-Time Scaling","created":"2025-03-01","cited_by_count":189,"area":"lr"},{"id":"2207.07051","title":"Language models show human-like content effects on reasoning tasks","created":"2022-07-14","cited_by_count":173,"area":"lr"},{"id":"2505.15134","title":"The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning","created":"2025-05-21","cited_by_count":166,"area":"lr"},{"id":"2205.11822","title":"Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations","created":"2022-05-24","cited_by_count":159,"area":"lr"},{"id":"2505.00949","title":"Llama-Nemotron: Efficient Reasoning Models","created":"2025-05-02","cited_by_count":158,"area":"lr"},{"id":"2410.02089","title":"RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning","created":"2024-10-02","cited_by_count":151,"area":"lr"},{"id":"2305.06599","title":"Structured Chain-of-Thought Prompting for Code Generation","created":"2023-05-11","cited_by_count":138,"area":"lr"},{"id":"2209.07686","title":"Text and Patterns: For Effective Chain of Thought, It Takes Two to Tango","created":"2022-09-16","cited_by_count":128,"area":"lr"},{"id":"2504.01943","title":"OpenCodeReasoning: Advancing Data Distillation for Competitive Coding","created":"2025-04-02","cited_by_count":113,"area":"lr"},{"id":"2305.14045","title":"The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning","created":"2023-05-23","cited_by_count":108,"area":"lr"},{"id":"2307.11768","title":"Question Decomposition Improves the Faithfulness of Model-Generated Reasoning","created":"2023-07-17","cited_by_count":108,"area":"lr"},{"id":"2401.10480","title":"Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step Reasoning","created":"2024-01-19","cited_by_count":108,"area":"lr"},{"id":"2501.19324","title":"Reward-Guided Speculative Decoding for Efficient LLM Reasoning","created":"2025-01-31","cited_by_count":106,"area":"lr"},{"id":"2502.20122","title":"Self-Training Elicits Concise Reasoning in Large Language Models","created":"2025-02-27","cited_by_count":99,"area":"lr"},{"id":"2502.02542","title":"OverThink: Slowdown Attacks on Reasoning LLMs","created":"2025-02-04","cited_by_count":96,"area":"lr"},{"id":"2310.11207","title":"Can Large Language Models Explain Themselves? A Study of LLM-Generated Self-Explanations","created":"2023-10-17","cited_by_count":90,"area":"lr"},{"id":"2502.18439","title":"MAPoRL: Multi-Agent Post-Co-Training for Collaborative Large Language Models with Reinforcement Learning","created":"2025-02-25","cited_by_count":86,"area":"lr"},{"id":"2603.11137","title":"Scaling Reasoning Efficiently via Relaxed On-Policy Distillation","created":"2026-03-11","cited_by_count":82,"area":"lr"},{"id":"2309.09117","title":"Contrastive Decoding Improves Reasoning in Large Language Models","created":"2023-09-17","cited_by_count":74,"area":"lr"},{"id":"2402.11451","title":"SciAgent: Tool-augmented Language Models for Scientific Reasoning","created":"2024-02-18","cited_by_count":70,"area":"lr"},{"id":"2312.03748","title":"Applying Large Language Models and Chain-of-Thought for Automatic Scoring","created":"2023-11-30","cited_by_count":69,"area":"lr"},{"id":"2508.02085","title":"SE-Agent: Self-Evolution Trajectory Optimization in Multi-Step Reasoning with LLM-Based Agents","created":"2025-08-04","cited_by_count":69,"area":"lr"},{"id":"2503.01422","title":"Sampling-Efficient Test-Time Scaling: Self-Estimating the Best-of-N Sampling in Early Decoding","created":"2025-03-03","cited_by_count":63,"area":"lr"},{"id":"2410.02052","title":"ExACT: Teaching AI Agents to Explore with Reflective-MCTS and Exploratory Learning","created":"2024-10-02","cited_by_count":62,"area":"lr"},{"id":"2302.00618","title":"Synthetic Prompting: Generating Chain-of-Thought Demonstrations for Large Language Models","created":"2023-02-01","cited_by_count":61,"area":"lr"},{"id":"2309.15028","title":"Don't throw away your value model! Generating more preferable text with Value-Guided Monte-Carlo Tree Search decoding","created":"2023-09-26","cited_by_count":60,"area":"lr"},{"id":"2403.18120","title":"Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalization","created":"2024-03-26","cited_by_count":55,"area":"lr"},{"id":"2501.18101","title":"Diverse Preference Optimization","created":"2025-01-30","cited_by_count":52,"area":"lr"},{"id":"2504.12522","title":"Evaluating the Diversity and Quality of LLM Generated Content","created":"2025-04-16","cited_by_count":51,"area":"lr"},{"id":"2505.17612","title":"Distilling LLM Agent into Small Models with Retrieval and Code Tools","created":"2025-05-23","cited_by_count":47,"area":"lr"},{"id":"2403.09972","title":"Think Twice Before Trusting: Self-Detection for Large Language Models through Comprehensive Answer Reflection","created":"2024-03-15","cited_by_count":41,"area":"lr"},{"id":"2506.09340","title":"RePO: Replay-Enhanced Policy Optimization","created":"2025-06-11","cited_by_count":39,"area":"lr"},{"id":"2504.10478","title":"Weight Ensembling Improves Reasoning in Language Models","created":"2025-04-14","cited_by_count":38,"area":"lr"},{"id":"2204.13074","title":"Towards Teachable Reasoning Systems: Using a Dynamic Memory of User Feedback for Continual System Improvement","created":"2022-04-27","cited_by_count":37,"area":"lr"},{"id":"2502.17407","title":"Linguistic Generalizability of Test-Time Scaling in Mathematical Reasoning","created":"2025-02-24","cited_by_count":37,"area":"lr"},{"id":"2402.01591","title":"BAT: Learning to Reason about Spatial Sounds with Large Language Models","created":"2024-02-02","cited_by_count":36,"area":"lr"},{"id":"2508.01491","title":"The Homogenizing Effect of Large Language Models on Human Expression and Thought","created":"2025-08-02","cited_by_count":35,"area":"lr"},{"id":"2502.05234","title":"Optimizing Temperature for Language Models with Multi-Sample Inference","created":"2025-02-07","cited_by_count":33,"area":"lr"},{"id":"2511.22018","title":"MedEyes: Learning Dynamic Visual Focus for Medical Progressive Diagnosis","created":"2025-11-27","cited_by_count":32,"area":"lr"},{"id":"2403.02738","title":"Causal Prompting: Debiasing Large Language Model Prompting based on Front-Door Adjustment","created":"2024-03-05","cited_by_count":30,"area":"lr"},{"id":"2406.05673","title":"Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples","created":"2024-06-09","cited_by_count":30,"area":"lr"},{"id":"2410.08105","title":"What Makes Large Language Models Reason in (Multi-Turn) Code Generation?","created":"2024-10-10","cited_by_count":29,"area":"lr"},{"id":"2405.18711","title":"Calibrating Reasoning in Language Models with Internal Consistency","created":"2024-05-29","cited_by_count":28,"area":"lr"},{"id":"2408.00802","title":"Leveraging LLM Reasoning Enhances Personalized Recommender Systems","created":"2024-07-22","cited_by_count":28,"area":"lr"},{"id":"2404.03204","title":"RALL-E: Robust Codec Language Modeling with Chain-of-Thought Prompting for Text-to-Speech Synthesis","created":"2024-04-04","cited_by_count":26,"area":"lr"},{"id":"2509.25133","title":"Rethinking Entropy Regularization in Large Reasoning Models","created":"2025-09-29","cited_by_count":26,"area":"lr"},{"id":"2509.25373","title":"From Perception to Cognition: A Survey of Vision-Language Interactive Reasoning in Multimodal Large Language Models","created":"2025-09-29","cited_by_count":26,"area":"lr"},{"id":"2305.04808","title":"CAT: A Contextualized Conceptualization and Instantiation Framework for Commonsense Reasoning","created":"2023-05-08","cited_by_count":25,"area":"lr"},{"id":"2409.12452","title":"Unlocking Reasoning Potential in Large Langauge Models by Scaling Code-form Planning","created":"2024-09-19","cited_by_count":25,"area":"lr"},{"id":"2502.01567","title":"Latent Thought Models with Variational Bayes Inference-Time Computation","created":"2025-02-03","cited_by_count":25,"area":"lr"},{"id":"2401.17686","title":"Deductive Beam Search: Decoding Deducible Rationale for Chain-of-Thought Reasoning","created":"2024-01-31","cited_by_count":24,"area":"lr"},{"id":"2407.05013","title":"Progress or Regress? Self-Improvement Reversal in Post-training","created":"2024-07-06","cited_by_count":23,"area":"lr"},{"id":"2501.10799","title":"Step-KTO: Optimizing Mathematical Reasoning through Stepwise Binary Feedback","created":"2025-01-18","cited_by_count":22,"area":"lr"},{"id":"2502.04790","title":"S$^2$-MAD: Breaking the Token Barrier to Enhance Multi-Agent Debate Efficiency","created":"2025-02-07","cited_by_count":22,"area":"lr"},{"id":"2503.21961","title":"Entropy-Gated Branching for Efficient Test-Time Reasoning","created":"2025-03-27","cited_by_count":22,"area":"lr"},{"id":"2602.10273","title":"Power-SMC: Low-Latency Sequence-Level Power Sampling for Training-Free LLM Reasoning","created":"2026-02-10","cited_by_count":21,"area":"lr"},{"id":"2306.07932","title":"Human-in-the-Loop through Chain-of-Thought","created":"2023-06-10","cited_by_count":20,"area":"lr"},{"id":"2505.22960","title":"Revisiting Multi-Agent Debate as Test-Time Scaling: A Systematic Study of Conditional Effectiveness","created":"2025-05-29","cited_by_count":20,"area":"lr"},{"id":"2603.22446","title":"Sparse but Critical: A Token-Level Analysis of Distributional Shifts in RLVR Fine-Tuning of LLMs","created":"2026-03-23","cited_by_count":20,"area":"lr"},{"id":"2604.06268","title":"RAGEN-2: Reasoning Collapse in Agentic RL","created":"2026-04-07","cited_by_count":20,"area":"lr"},{"id":"2203.07285","title":"Diversifying Content Generation for Commonsense Reasoning with Mixture of Knowledge Graph Experts","created":"2022-03-14","cited_by_count":19,"area":"lr"},{"id":"2404.16807","title":"Improving Diversity of Commonsense Generation by Large Language Models via In-Context Learning","created":"2024-04-25","cited_by_count":19,"area":"lr"},{"id":"2311.08154","title":"Just Ask One More Time! Self-Agreement Improves Reasoning of Language Models in (Almost) All Scenarios","created":"2023-11-14","cited_by_count":18,"area":"lr"},{"id":"2501.16207","title":"From Informal to Formal -- Incorporating and Evaluating LLMs on Natural Language Requirements to Verifiable Formal Proofs","created":"2025-01-27","cited_by_count":18,"area":"lr"},{"id":"2601.19921","title":"Demystifying Multi-Agent Debate: The Role of Confidence and Diversity","created":"2026-01-09","cited_by_count":18,"area":"lr"},{"id":"2312.01279","title":"TextGenSHAP: Scalable Post-hoc Explanations in Text Generation with Long Documents","created":"2023-12-03","cited_by_count":17,"area":"lr"},{"id":"2601.09088","title":"Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning","created":"2026-01-14","cited_by_count":17,"area":"lr"},{"id":"2602.20710","title":"Counterfactual Simulation Training for Chain-of-Thought Faithfulness","created":"2026-02-24","cited_by_count":17,"area":"lr"},{"id":"2209.07662","title":"NELLIE: A Neuro-Symbolic Inference Engine for Grounded, Compositional, and Explainable Reasoning","created":"2022-09-16","cited_by_count":16,"area":"lr"},{"id":"2505.23363","title":"Discriminative Policy Optimization for Token-Level Reward Models","created":"2025-05-29","cited_by_count":16,"area":"lr"},{"id":"2506.09532","title":"Athena: Enhancing Multimodal Reasoning with Data-efficient Process Reward Models","created":"2025-06-11","cited_by_count":16,"area":"lr"},{"id":"2512.23032","title":"Is Chain-of-Thought Really Not Explainability? Chain-of-Thought Can Be Faithful without Hint Verbalization","created":"2025-12-28","cited_by_count":16,"area":"lr"},{"id":"2502.07191","title":"Bag of Tricks for Inference-time Computation of LLM Reasoning","created":"2025-02-11","cited_by_count":15,"area":"lr"},{"id":"2510.04265","title":"Don't Pass@k: A Bayesian Framework for Large Language Model Evaluation","created":"2025-10-05","cited_by_count":15,"area":"lr"},{"id":"2310.05861","title":"Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models","created":"2023-10-09","cited_by_count":14,"area":"lr"},{"id":"2402.08147","title":"VerMCTS: Synthesizing Multi-Step Programs using a Verifier, a Large Language Model, and Tree Search","created":"2024-02-13","cited_by_count":14,"area":"lr"},{"id":"2510.24051","title":"Pie: A Programmable Serving System for Emerging LLM Applications","created":"2025-10-28","cited_by_count":14,"area":"lr"},{"id":"2403.07872","title":"Rethinking Generative Large Language Model Evaluation for Semantic Comprehension","created":"2024-03-12","cited_by_count":13,"area":"lr"},{"id":"2406.17642","title":"Banishing LLM Hallucinations Requires Rethinking Generalization","created":"2024-06-25","cited_by_count":13,"area":"lr"},{"id":"2410.10735","title":"Embedding Self-Correction as an Inherent Ability in Large Language Models for Enhanced Mathematical Reasoning","created":"2024-10-14","cited_by_count":13,"area":"lr"},{"id":"2312.05180","title":"PathFinder: Guided Search over Multi-Step Reasoning Paths","created":"2023-12-08","cited_by_count":12,"area":"lr"},{"id":"2502.12123","title":"On the Query Complexity of Verifier-Assisted Language Generation","created":"2025-02-17","cited_by_count":12,"area":"lr"}],"next_cursor":"100"}