{"total":202,"rows":[{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139,"area":"lr"},{"id":"2403.07974","title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","created":"2024-03-12","cited_by_count":2004,"area":"lr"},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807,"area":"lr"},{"id":"2305.14325","title":"Improving Factuality and Reasoning in Language Models through Multiagent Debate","created":"2023-05-23","cited_by_count":1784,"area":"lr"},{"id":"2206.14858","title":"Solving Quantitative Reasoning Problems with Language Models","created":"2022-06-29","cited_by_count":1392,"area":"lr"},{"id":"2305.15334","title":"Gorilla: Large Language Model Connected with Massive APIs","created":"2023-05-24","cited_by_count":1332,"area":"lr"},{"id":"2304.05128","title":"Teaching Large Language Models to Self-Debug","created":"2023-04-11","cited_by_count":988,"area":"lr"},{"id":"2305.11738","title":"CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing","created":"2023-05-19","cited_by_count":783,"area":"lr"},{"id":"2502.01456","title":"Process Reinforcement through Implicit Rewards","created":"2025-02-03","cited_by_count":504,"area":"lr"},{"id":"2502.03387","title":"LIMO: Less is More for Reasoning","created":"2025-02-05","cited_by_count":498,"area":"lr"},{"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":"2306.08647","title":"Language to Rewards for Robotic Skill Synthesis","created":"2023-06-14","cited_by_count":312,"area":"lr"},{"id":"2506.04178","title":"OpenThoughts: Data Recipes for Reasoning Models","created":"2025-06-04","cited_by_count":304,"area":"lr"},{"id":"2502.18449","title":"SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution","created":"2025-02-25","cited_by_count":263,"area":"lr"},{"id":"2402.14658","title":"OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement","created":"2024-02-22","cited_by_count":247,"area":"lr"},{"id":"2302.08468","title":"LEVER: Learning to Verify Language-to-Code Generation with Execution","created":"2023-02-16","cited_by_count":239,"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":"2505.19590","title":"Learning to Reason without External Rewards","created":"2025-05-26","cited_by_count":210,"area":"lr"},{"id":"2311.17311","title":"Universal Self-Consistency for Large Language Model Generation","created":"2023-11-29","cited_by_count":203,"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":"2601.05242","title":"GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization","created":"2026-01-08","cited_by_count":193,"area":"lr"},{"id":"2405.11403","title":"MapCoder: Multi-Agent Code Generation for Competitive Problem Solving","created":"2024-05-18","cited_by_count":177,"area":"lr"},{"id":"2504.07164","title":"R2E-Gym: Procedural Environments and Hybrid Verifiers for Scaling Open-Weights SWE Agents","created":"2025-04-09","cited_by_count":158,"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":"2410.01943","title":"CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL","created":"2024-10-02","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":"2312.04474","title":"Chain of Code: Reasoning with a Language Model-Augmented Code Emulator","created":"2023-12-07","cited_by_count":123,"area":"lr"},{"id":"2503.02951","title":"KodCode: A Diverse, Challenging, and Verifiable Synthetic Dataset for Coding","created":"2025-03-04","cited_by_count":119,"area":"lr"},{"id":"2305.11860","title":"Let's Sample Step by Step: Adaptive-Consistency for Efficient Reasoning and Coding with LLMs","created":"2023-05-19","cited_by_count":115,"area":"lr"},{"id":"2501.01257","title":"CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings","created":"2025-01-02","cited_by_count":115,"area":"lr"},{"id":"2504.01943","title":"OpenCodeReasoning: Advancing Data Distillation for Competitive Coding","created":"2025-04-02","cited_by_count":113,"area":"lr"},{"id":"2506.02177","title":"Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts","created":"2025-06-02","cited_by_count":113,"area":"lr"},{"id":"2403.07816","title":"Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM","created":"2024-03-12","cited_by_count":109,"area":"lr"},{"id":"2310.01714","title":"Large Language Models as Analogical Reasoners","created":"2023-10-03","cited_by_count":107,"area":"lr"},{"id":"2505.22660","title":"Maximizing Confidence Alone Improves Reasoning","created":"2025-05-28","cited_by_count":100,"area":"lr"},{"id":"2502.14382","title":"S*: Test Time Scaling for Code Generation","created":"2025-02-20","cited_by_count":98,"area":"lr"},{"id":"2510.14901","title":"Reasoning with Sampling: Your Base Model is Smarter Than You Think","created":"2025-10-16","cited_by_count":89,"area":"lr"},{"id":"2402.01391","title":"StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback","created":"2024-02-02","cited_by_count":77,"area":"lr"},{"id":"2402.08939","title":"Premise Order Matters in Reasoning with Large Language Models","created":"2024-02-14","cited_by_count":72,"area":"lr"},{"id":"2406.12753","title":"OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI","created":"2024-06-18","cited_by_count":71,"area":"lr"},{"id":"2410.04707","title":"Learning How Hard to Think: Input-Adaptive Allocation of LM Computation","created":"2024-10-07","cited_by_count":70,"area":"lr"},{"id":"2504.14655","title":"LeetCodeDataset: A Temporal Dataset for Robust Evaluation and Efficient Training of Code LLMs","created":"2025-04-20","cited_by_count":70,"area":"lr"},{"id":"2212.10561","title":"Parsel: Algorithmic Reasoning with Language Models by Composing Decompositions","created":"2022-12-20","cited_by_count":64,"area":"lr"},{"id":"2502.12289","title":"Evaluating Step-by-step Reasoning Traces: A Survey","created":"2025-02-17","cited_by_count":63,"area":"lr"},{"id":"2502.20379","title":"Multi-Agent Verification: Scaling Test-Time Compute with Multiple Verifiers","created":"2025-02-27","cited_by_count":62,"area":"lr"},{"id":"2411.02272","title":"Combining Induction and Transduction for Abstract Reasoning","created":"2024-11-04","cited_by_count":53,"area":"lr"},{"id":"2503.04412","title":"Wider or Deeper? Scaling LLM Inference-Time Compute with Adaptive Branching Tree Search","created":"2025-03-06","cited_by_count":51,"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":"2411.04109","title":"Self-Consistency Preference Optimization","created":"2024-11-06","cited_by_count":50,"area":"lr"},{"id":"2309.17272","title":"Enhancing Large Language Models in Coding Through Multi-Perspective Self-Consistency","created":"2023-09-29","cited_by_count":46,"area":"lr"},{"id":"2506.05817","title":"CodeContests+: High-Quality Test Case Generation for Competitive Programming","created":"2025-06-06","cited_by_count":46,"area":"lr"},{"id":"2506.18896","title":"ReasonFlux-PRM: Trajectory-Aware PRMs for Long Chain-of-Thought Reasoning in LLMs","created":"2025-06-23","cited_by_count":46,"area":"lr"},{"id":"2504.04736","title":"Synthetic Data Generation & Multi-Step RL for Reasoning & Tool Use","created":"2025-04-07","cited_by_count":45,"area":"lr"},{"id":"2507.13266","title":"QuestA: Expanding Reasoning Capacity in LLMs via Question Augmentation","created":"2025-07-17","cited_by_count":44,"area":"lr"},{"id":"2502.03492","title":"Teaching Language Models to Critique via Reinforcement Learning","created":"2025-02-05","cited_by_count":42,"area":"lr"},{"id":"2505.05849","title":"AgentVigil: Generic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents","created":"2025-05-09","cited_by_count":42,"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":"2502.06737","title":"VersaPRM: Multi-Domain Process Reward Model via Synthetic Reasoning Data","created":"2025-02-10","cited_by_count":40,"area":"lr"},{"id":"2507.15778","title":"Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVR","created":"2025-07-21","cited_by_count":39,"area":"lr"},{"id":"2205.14318","title":"Learning Math Reasoning from Self-Sampled Correct and Partially-Correct Solutions","created":"2022-05-28","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":"2411.04329","title":"CodeTree: Agent-guided Tree Search for Code Generation with Large Language Models","created":"2024-11-07","cited_by_count":34,"area":"lr"},{"id":"2502.06533","title":"Ignore the KL Penalty! Boosting Exploration on Critical Tokens to Enhance RL Fine-Tuning","created":"2025-02-10","cited_by_count":34,"area":"lr"},{"id":"2310.14053","title":"Beyond Accuracy: Evaluating Self-Consistency of Code Large Language Models with IdentityChain","created":"2023-10-21","cited_by_count":31,"area":"lr"},{"id":"2308.08784","title":"CodeCoT: Tackling Code Syntax Errors in CoT Reasoning for Code Generation","created":"2023-08-17","cited_by_count":29,"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":"2501.14275","title":"Leveraging Online Olympiad-Level Math Problems for LLMs Training and Contamination-Resistant Evaluation","created":"2025-01-24","cited_by_count":29,"area":"lr"},{"id":"2502.20127","title":"SoRFT: Issue Resolving with Subtask-oriented Reinforced Fine-Tuning","created":"2025-02-27","cited_by_count":28,"area":"lr"},{"id":"2312.05562","title":"Chain-of-Thought in Neural Code Generation: From and For Lightweight Language Models","created":"2023-12-09","cited_by_count":27,"area":"lr"},{"id":"2506.16395","title":"OJBench: A Competition Level Code Benchmark For Large Language Models","created":"2025-06-19","cited_by_count":26,"area":"lr"},{"id":"2312.02143","title":"Competition-Level Problems are Effective LLM Evaluators","created":"2023-12-04","cited_by_count":25,"area":"lr"},{"id":"2507.09075","title":"OpenCodeReasoning-II: A Simple Test Time Scaling Approach via Self-Critique","created":"2025-07-11","cited_by_count":25,"area":"lr"},{"id":"2510.01180","title":"BroRL: Scaling Reinforcement Learning via Broadened Exploration","created":"2025-10-01","cited_by_count":25,"area":"lr"},{"id":"2505.24098","title":"HardTests: Synthesizing High-Quality Test Cases for LLM Coding","created":"2025-05-30","cited_by_count":23,"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":"2503.15952","title":"Adaptive Group Policy Optimization: Towards Stable Training and Token-Efficient Reasoning","created":"2025-03-20","cited_by_count":21,"area":"lr"},{"id":"2507.04136","title":"A Technical Survey of Reinforcement Learning Techniques for Large Language Models","created":"2025-07-05","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":"2505.15817","title":"Learning to Reason via Mixture-of-Thought for Logical Reasoning","created":"2025-05-21","cited_by_count":20,"area":"lr"},{"id":"2409.17270","title":"Proof of Thought : Neurosymbolic Program Synthesis allows Robust and Interpretable Reasoning","created":"2024-09-25","cited_by_count":19,"area":"lr"},{"id":"2509.26314","title":"Latent Thinking Optimization: Your Latent Reasoning Language Model Secretly Encodes Reward Signals in Its Latent Thoughts","created":"2025-09-30","cited_by_count":19,"area":"lr"},{"id":"2506.11442","title":"ReVeal: Self-Evolving Code Agents via Reliable Self-Verification","created":"2025-06-13","cited_by_count":18,"area":"lr"},{"id":"2508.04349","title":"GTPO and GRPO-S: Token and Sequence-Level Reward Shaping with Policy Entropy","created":"2025-08-06","cited_by_count":18,"area":"lr"},{"id":"2511.09092","title":"OR-R1: Automating Modeling and Solving of Operations Research Optimization Problem via Test-Time Reinforcement Learning","created":"2025-11-12","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":"2308.01906","title":"Reasoning in Large Language Models Through Symbolic Math Word Problems","created":"2023-08-03","cited_by_count":16,"area":"lr"},{"id":"2410.22480","title":"Scaling LLM Inference with Optimized Sample Compute Allocation","created":"2024-10-29","cited_by_count":16,"area":"lr"},{"id":"2502.20868","title":"ProBench: Benchmarking Large Language Models in Competitive Programming","created":"2025-02-28","cited_by_count":15,"area":"lr"},{"id":"2508.03012","title":"Tool-integrated Reinforcement Learning for Repo Deep Search","created":"2025-08-05","cited_by_count":15,"area":"lr"},{"id":"2507.06920","title":"Rethinking Verification for LLM Code Generation: From Generation to Testing","created":"2025-07-09","cited_by_count":14,"area":"lr"},{"id":"2602.14338","title":"Train Less, Learn More: Adaptive Efficient Rollout Optimization for Group-Based Reinforcement Learning","created":"2026-02-15","cited_by_count":14,"area":"lr"},{"id":"2310.09107","title":"GLoRE: Evaluating Logical Reasoning of Large Language Models","created":"2023-10-13","cited_by_count":13,"area":"lr"},{"id":"2304.01665","title":"Mastering Symbolic Operations: Augmenting Language Models with Compiled Neural Networks","created":"2023-04-04","cited_by_count":12,"area":"lr"},{"id":"2309.11054","title":"Design of Chain-of-Thought in Math Problem Solving","created":"2023-09-20","cited_by_count":12,"area":"lr"},{"id":"2502.02390","title":"CoAT: Chain-of-Associated-Thoughts Framework for Enhancing Large Language Models Reasoning","created":"2025-02-04","cited_by_count":12,"area":"lr"},{"id":"2507.12399","title":"ROC-n-reroll: How verifier imperfection affects test-time scaling","created":"2025-07-16","cited_by_count":12,"area":"lr"},{"id":"2509.23232","title":"SPEC-RL: Accelerating On-Policy Reinforcement Learning with Speculative Rollouts","created":"2025-09-27","cited_by_count":12,"area":"lr"},{"id":"2601.22129","title":"SWE-Replay: Efficient Test-Time Scaling for Software Engineering Agents","created":"2026-01-29","cited_by_count":12,"area":"lr"}],"next_cursor":"100"}