{"total":69,"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":"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":"2310.04406","title":"Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models","created":"2023-10-06","cited_by_count":574,"area":"lr"},{"id":"2601.20802","title":"Reinforcement Learning via Self-Distillation","created":"2026-01-28","cited_by_count":332,"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":"2302.08468","title":"LEVER: Learning to Verify Language-to-Code Generation with Execution","created":"2023-02-16","cited_by_count":239,"area":"lr"},{"id":"2308.03188","title":"Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies","created":"2023-08-06","cited_by_count":238,"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":"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":"2305.06599","title":"Structured Chain-of-Thought Prompting for Code Generation","created":"2023-05-11","cited_by_count":138,"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":"2502.14382","title":"S*: Test Time Scaling for Code Generation","created":"2025-02-20","cited_by_count":98,"area":"lr"},{"id":"2502.01718","title":"ACECODER: Acing Coder RL via Automated Test-Case Synthesis","created":"2025-02-03","cited_by_count":93,"area":"lr"},{"id":"2311.08516","title":"LLMs cannot find reasoning errors, but can correct them given the error location","created":"2023-11-14","cited_by_count":85,"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":"2412.20993","title":"Efficiently Scaling LLM Reasoning with Certaindex","created":"2024-12-30","cited_by_count":58,"area":"lr"},{"id":"2505.21297","title":"rStar-Coder: Scaling Competitive Code Reasoning with a Large-Scale Verified Dataset","created":"2025-05-27","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":"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":"2502.12468","title":"MCTS-Judge: Test-Time Scaling in LLM-as-a-Judge for Code Correctness Evaluation","created":"2025-02-18","cited_by_count":32,"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":"2412.17256","title":"B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners","created":"2024-12-23","cited_by_count":26,"area":"lr"},{"id":"2503.10814","title":"Thinking Machines: A Survey of LLM based Reasoning Strategies","created":"2025-03-13","cited_by_count":25,"area":"lr"},{"id":"2508.05170","title":"ReCode: Reinforcing Code Generation with Reasoning-Process Rewards","created":"2025-08-07","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":"2410.12381","title":"HumanEval-V: Benchmarking High-Level Visual Reasoning with Complex Diagrams in Coding Tasks","created":"2024-10-16","cited_by_count":20,"area":"lr"},{"id":"2403.13271","title":"Enhancing Code Generation Performance of Smaller Models by Distilling the Reasoning Ability of LLMs","created":"2024-03-20","cited_by_count":17,"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":"2506.00391","title":"SHARE: An SLM-based Hierarchical Action CorREction Assistant for Text-to-SQL","created":"2025-05-31","cited_by_count":16,"area":"lr"},{"id":"2502.07803","title":"Reasoning-as-Logic-Units: Scaling Test-Time Reasoning in Large Language Models Through Logic Unit Alignment","created":"2025-02-05","cited_by_count":12,"area":"lr"},{"id":"2411.05010","title":"Scattered Forest Search: Smarter Code Space Exploration with LLMs","created":"2024-10-22","cited_by_count":10,"area":"lr"},{"id":"2502.13820","title":"Scoring Verifiers: Evaluating Synthetic Verification for Code and Reasoning","created":"2025-02-19","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":"2502.15835","title":"Pragmatic Reasoning improves LLM Code Generation","created":"2025-02-20","cited_by_count":7,"area":"lr"},{"id":"2503.19599","title":"HoarePrompt: Structural Reasoning About Program Correctness in Natural Language","created":"2025-03-25","cited_by_count":7,"area":"lr"},{"id":"2603.12698","title":"EvolveCoder: Evolving Test Cases via Adversarial Verification for Code Reinforcement Learning","created":"2026-03-13","cited_by_count":5,"area":"lr"},{"id":"2403.16921","title":"PropTest: Automatic Property Testing for Improved Visual Programming","created":"2024-03-25","cited_by_count":4,"area":"lr"},{"id":"2404.07549","title":"Comments as Natural Logic Pivots: Improve Code Generation via Comment Perspective","created":"2024-04-11","cited_by_count":3,"area":"lr"},{"id":"2410.19245","title":"MaCTG: Multi-Agent Collaborative Thought Graph for Automatic Programming","created":"2024-10-25","cited_by_count":3,"area":"lr"},{"id":"2601.20379","title":"Policy of Thoughts: Scaling Test-Time Training for LLM Reasoning via Online Policy Evolution","created":"2026-01-28","cited_by_count":3,"area":"lr"},{"id":"2505.17482","title":"From Reasoning to Generalization: Knowledge-Augmented LLMs for ARC Benchmark","created":"2025-05-23","cited_by_count":2,"area":"lr"},{"id":"2605.07248","title":"PaT: Planning-after-Trial for Efficient Test-Time Code Generation","created":"2026-05-08","cited_by_count":2,"area":"lr"},{"id":"2605.17609","title":"Adaptive Generate-Rank-Verify: Inference-Time Search with Costly Verification","created":"2026-05-17","cited_by_count":2,"area":"lr"},{"id":"2605.17626","title":"Verifier-Guided Code Translation via Meta-Step Decoding","created":"2026-05-17","cited_by_count":2,"area":"lr"},{"id":"2607.17531","title":"Oracle Gap and Signal Fidelity: A Fixed-Pool Diagnostic for Test-Time Collaboration","created":"2026-07-20","cited_by_count":2,"area":"lr"},{"id":"2503.18494","title":"Verbal Process Supervision Elicits Better Coding Agents","created":"2025-03-24","cited_by_count":1,"area":"lr"},{"id":"2510.17868","title":"UniCode: Augmenting Evaluation for Code Reasoning","created":"2025-10-16","cited_by_count":1,"area":"lr"},{"id":"2601.22803","title":"CVeDRL: An Efficient Code Verifier via Difficulty-aware Reinforcement Learning","created":"2026-01-30","cited_by_count":1,"area":"lr"},{"id":"2603.01409","title":"MIST-RL: Mutation-based Incremental Suite Testing via Reinforcement Learning","created":"2026-03-02","cited_by_count":1,"area":"lr"},{"id":"2508.08983","title":"Rational Inverse Reasoning: Few-Shot Imitation by Inferring Intent through Planning","created":"2025-08-12","cited_by_count":0,"area":"lr"},{"id":"2509.00465","title":"Embodied Spatial Intelligence: from Implicit Scene Modeling to Spatial Reasoning","created":"2025-08-30","cited_by_count":0,"area":"lr"},{"id":"2509.01308","title":"GradeSQL: Test-Time Inference with Outcome Reward Models for Text-to-SQL Generation from Large Language Models","created":"2025-09-01","cited_by_count":0,"area":"lr"},{"id":"2512.00127","title":"Generating Verifiable Chain of Thoughts from Exection-Traces","created":"2025-11-28","cited_by_count":0,"area":"lr"},{"id":"2602.14054","title":"LogitsCoder: Towards Efficient Chain-of-Thought Path Search via Logits Preference Decoding for Code Generation","created":"2026-02-15","cited_by_count":0,"area":"lr"},{"id":"2605.08658","title":"Sketch-and-Verify: Structured Inference-Time Scaling via Program Sketching","created":"2026-05-09","cited_by_count":0,"area":"lr"},{"id":"2605.14215","title":"GenCircuit-RL: Reinforcement Learning from Hierarchical Verification for Genetic Circuit Design","created":"2026-05-14","cited_by_count":0,"area":"lr"},{"id":"2606.16154","title":"A Gradient Perspective on RLVR Stability and Winner Advantage Policy Optimization","created":"2026-06-15","cited_by_count":0,"area":"lr"},{"id":"2607.07748","title":"Selective Left-Shift: Turning Test-Time Compute and Difficulty-based Curation into Training Data for Low-Resource Code Generation","created":"2026-07-08","cited_by_count":0,"area":"lr"},{"id":"2608.04459","title":"AdaptAgent: A Multi-agent, Domain-Guided Reasoning Framework for Code Adaptation","created":"2026-08-05","cited_by_count":0,"area":"lr"},{"id":"2609.12243","title":"Chopthin-Consensus Power Sampling: A Diversity-Preserving Approach to LLM Decoding","created":"2026-09-10","cited_by_count":0,"area":"lr"},{"id":"2609.16076","title":"The Imitation Game: When LLMs Learn to Reason Like Programs via Code-Centric Reasoning Data Synthesis","created":"2026-09-13","cited_by_count":0,"area":"lr"},{"id":"2609.33155","title":"Where Do Test-Time Scaling and Training Fall Short in Individual Stance Prediction?","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2610.05170","title":"Verification Trap: Understanding Test-Time Selection Failures under False Premises in Code Generation","created":"2026-10-04","cited_by_count":0,"area":"lr"},{"id":"2610.18760","title":"Beyond the Verdict: Agentic Code Judging with Verifiable Feedback","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}