{"total":191,"rows":[{"id":"2207.10397","title":"CodeT: Code Generation with Generated Tests","created":"2022-07-21","cited_by_count":384,"area":null},{"id":"2305.07922","title":"CodeT5+: Open Code Large Language Models for Code Understanding and Generation","created":"2023-05-13","cited_by_count":333,"area":null},{"id":"2401.03065","title":"CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution","created":"2024-01-05","cited_by_count":300,"area":null},{"id":"2211.00053","title":"Generating Sequences by Learning to Self-Correct","created":"2022-10-31","cited_by_count":277,"area":null},{"id":"2406.01297","title":"When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMs","created":"2024-06-03","cited_by_count":240,"area":null},{"id":"2306.14898","title":"InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback","created":"2023-06-26","cited_by_count":238,"area":null},{"id":"2306.09896","title":"Is Self-Repair a Silver Bullet for Code Generation?","created":"2023-06-16","cited_by_count":197,"area":null},{"id":"2303.05510","title":"Planning with Large Language Models for Code Generation","created":"2023-03-09","cited_by_count":182,"area":null},{"id":"2405.20003","title":"Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities","created":"2024-05-30","cited_by_count":159,"area":null},{"id":"2302.05319","title":"Large Language Models for Code: Security Hardening and Adversarial Testing","created":"2023-02-10","cited_by_count":155,"area":null},{"id":"2212.09420","title":"Large Language Models Meet NL2Code: A Survey","created":"2022-12-19","cited_by_count":138,"area":null},{"id":"2307.04349","title":"RLTF: Reinforcement Learning from Unit Test Feedback","created":"2023-07-10","cited_by_count":114,"area":null},{"id":"2405.12819","title":"Large Language Models Meet NLP: A Survey","created":"2024-05-21","cited_by_count":103,"area":null},{"id":"2305.13009","title":"Textually Pretrained Speech Language Models","created":"2023-05-22","cited_by_count":101,"area":null},{"id":"2301.13816","title":"Execution-based Code Generation using Deep Reinforcement Learning","created":"2023-01-31","cited_by_count":99,"area":null},{"id":"2207.14502","title":"Language Models Can Teach Themselves to Program Better","created":"2022-07-29","cited_by_count":78,"area":null},{"id":"2404.10952","title":"Can Language Models Solve Olympiad Programming?","created":"2024-04-16","cited_by_count":72,"area":null},{"id":"2307.14936","title":"PanGu-Coder2: Boosting Large Language Models for Code with Ranking Feedback","created":"2023-07-27","cited_by_count":69,"area":null},{"id":"2410.24198","title":"SelfCodeAlign: Self-Alignment for Code Generation","created":"2024-10-31","cited_by_count":62,"area":null},{"id":"2310.08992","title":"CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules","created":"2023-10-13","cited_by_count":58,"area":null},{"id":"2407.06153","title":"What's Wrong with Your Code Generated by Large Language Models? An Extensive Study","created":"2024-07-08","cited_by_count":53,"area":null},{"id":"2405.17503","title":"Code Repair with LLMs gives an Exploration-Exploitation Tradeoff","created":"2024-05-26","cited_by_count":51,"area":null},{"id":"2405.18649","title":"LeDex: Training LLMs to Better Self-Debug and Explain Code","created":"2024-05-28","cited_by_count":40,"area":null},{"id":"2507.05687","title":"AutoTriton: Automatic Triton Programming with Reinforcement Learning in LLMs","created":"2025-07-08","cited_by_count":40,"area":null},{"id":"2307.02503","title":"Natural Language Generation and Understanding of Big Code for AI-Assisted Programming: A Review","created":"2023-07-04","cited_by_count":32,"area":null},{"id":"2402.06853","title":"History, Development, and Principles of Large Language Models-An Introductory Survey","created":"2024-02-10","cited_by_count":30,"area":null},{"id":"2502.19148","title":"Amulet: ReAlignment During Test Time for Personalized Preference Adaptation of LLMs","created":"2025-02-26","cited_by_count":29,"area":null},{"id":"2305.00909","title":"Outline, Then Details: Syntactically Guided Coarse-To-Fine Code Generation","created":"2023-04-28","cited_by_count":27,"area":null},{"id":"2311.14904","title":"LLM-Assisted Code Cleaning For Training Accurate Code Generators","created":"2023-11-25","cited_by_count":27,"area":null},{"id":"2406.08316","title":"Is Programming by Example solved by LLMs?","created":"2024-06-12","cited_by_count":27,"area":null},{"id":"2410.17621","title":"Process Supervision-Guided Policy Optimization for Code Generation","created":"2024-10-23","cited_by_count":26,"area":null},{"id":"2305.10314","title":"LeTI: Learning to Generate from Textual Interactions","created":"2023-05-17","cited_by_count":25,"area":null},{"id":"2412.03578","title":"PerfCodeGen: Improving Performance of LLM Generated Code with Execution Feedback","created":"2024-11-18","cited_by_count":24,"area":null},{"id":"2510.18471","title":"CodeRL+: Improving Code Generation via Reinforcement with Execution Semantics Alignment","created":"2025-10-21","cited_by_count":24,"area":null},{"id":"2306.06755","title":"CoTran: An LLM-based Code Translator using Reinforcement Learning with Feedback from Compiler and Symbolic Execution","created":"2023-06-11","cited_by_count":22,"area":null},{"id":"2307.02435","title":"Exploring Continual Learning for Code Generation Models","created":"2023-07-05","cited_by_count":22,"area":null},{"id":"2504.14757","title":"SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World Bugs","created":"2025-04-20","cited_by_count":22,"area":null},{"id":"2306.00029","title":"CodeTF: One-stop Transformer Library for State-of-the-art Code LLMs","created":"2023-05-31","cited_by_count":21,"area":null},{"id":"2401.05443","title":"LLM4PLC: Harnessing Large Language Models for Verifiable Programming of PLCs in Industrial Control Systems","created":"2024-01-08","cited_by_count":21,"area":null},{"id":"2410.21157","title":"M2rc-Eval: Massively Multilingual Repository-level Code Completion Evaluation","created":"2024-10-28","cited_by_count":21,"area":null},{"id":"2406.19783","title":"NLPerturbator: Studying the Robustness of Code LLMs to Natural Language Variations","created":"2024-06-28","cited_by_count":20,"area":null},{"id":"2510.19944","title":"Seed3D 1.0: From Images to High-Fidelity Simulation-Ready 3D Assets","created":"2025-10-22","cited_by_count":20,"area":null},{"id":"2309.04316","title":"Incremental Learning of Humanoid Robot Behavior from Natural Interaction and Large Language Models","created":"2023-09-08","cited_by_count":19,"area":null},{"id":"2310.08678","title":"Can GPT models be Financial Analysts? An Evaluation of ChatGPT and GPT-4 on mock CFA Exams","created":"2023-10-12","cited_by_count":18,"area":null},{"id":"2310.03173","title":"$\\mathcal{B}$-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis","created":"2023-10-04","cited_by_count":17,"area":null},{"id":"2510.08439","title":"xRouter: Training Cost-Aware LLMs Orchestration System via Reinforcement Learning","created":"2025-10-09","cited_by_count":17,"area":null},{"id":"2305.14129","title":"GrACE: Generation using Associated Code Edits","created":"2023-05-23","cited_by_count":16,"area":null},{"id":"2306.14583","title":"Exploring the Robustness of Large Language Models for Solving Programming Problems","created":"2023-06-26","cited_by_count":16,"area":null},{"id":"2503.17502","title":"Large Language Models (LLMs) for Source Code Analysis: applications, models and datasets","created":"2025-03-21","cited_by_count":16,"area":null},{"id":"2505.16975","title":"SWE-Dev: Evaluating and Training Autonomous Feature-Driven Software Development","created":"2025-05-22","cited_by_count":16,"area":null},{"id":"2310.06680","title":"Benchmarking and Explaining Large Language Model-based Code Generation: A Causality-Centric Approach","created":"2023-10-10","cited_by_count":15,"area":null},{"id":"2407.00456","title":"Beyond Functional Correctness: Investigating Coding Style Inconsistencies in Large Language Models","created":"2024-06-29","cited_by_count":15,"area":null},{"id":"2407.18271","title":"Large Language Model for Verilog Generation with Code-Structure-Guided Reinforcement Learning","created":"2024-07-21","cited_by_count":15,"area":null},{"id":"2303.09128","title":"Exploring Distributional Shifts in Large Language Models for Code Analysis","created":"2023-03-16","cited_by_count":14,"area":null},{"id":"2307.08220","title":"FRANC: A Lightweight Framework for High-Quality Code Generation","created":"2023-07-17","cited_by_count":14,"area":null},{"id":"2309.09826","title":"Efficient Avoidance of Vulnerabilities in Auto-completed Smart Contract Code Using Vulnerability-constrained Decoding","created":"2023-09-18","cited_by_count":14,"area":null},{"id":"2305.18342","title":"Neural Task Synthesis for Visual Programming","created":"2023-05-26","cited_by_count":13,"area":null},{"id":"2305.18498","title":"ANPL: Towards Natural Programming with Interactive Decomposition","created":"2023-05-29","cited_by_count":13,"area":null},{"id":"2405.16450","title":"Synthesizing Programmatic Reinforcement Learning Policies with Large Language Model Guided Search","created":"2024-05-26","cited_by_count":13,"area":null},{"id":"2412.18573","title":"Top General Performance = Top Domain Performance? DomainCodeBench: A Multi-domain Code Generation Benchmark","created":"2024-12-24","cited_by_count":13,"area":null},{"id":"2311.13721","title":"Nova: Generative Language Models for Assembly Code with Hierarchical Attention and Contrastive Learning","created":"2023-11-22","cited_by_count":12,"area":null},{"id":"2505.22704","title":"Training Language Models to Generate Quality Code with Program Analysis Feedback","created":"2025-05-28","cited_by_count":12,"area":null},{"id":"2304.01102","title":"RunBugRun -- An Executable Dataset for Automated Program Repair","created":"2023-04-03","cited_by_count":11,"area":null},{"id":"2308.14328","title":"Reinforcement Learning for Generative AI: A Survey","created":"2023-08-28","cited_by_count":11,"area":null},{"id":"2408.07461","title":"Problem Solving Through Human-AI Preference-Based Cooperation","created":"2024-08-14","cited_by_count":11,"area":null},{"id":"2604.10701","title":"Bringing Value Models Back: Generative Critics for Value Modeling in LLM Reinforcement Learning","created":"2026-04-12","cited_by_count":11,"area":null},{"id":"2605.07442","title":"GameGen-Verifier: Parallel Keypoint-Based Verification for LLM-Generated Games via Runtime State Injection","created":"2026-05-08","cited_by_count":11,"area":null},{"id":"2303.00732","title":"R-U-SURE? Uncertainty-Aware Code Suggestions By Maximizing Utility Across Random User Intents","created":"2023-03-01","cited_by_count":10,"area":null},{"id":"2308.00031","title":"Reinforcement Learning for Generative AI: State of the Art, Opportunities and Open Research Challenges","created":"2023-07-31","cited_by_count":10,"area":null},{"id":"2409.08692","title":"B4: Towards Optimal Assessment of Plausible Code Solutions with Plausible Tests","created":"2024-09-13","cited_by_count":9,"area":null},{"id":"2312.05657","title":"PerfRL: A Small Language Model Framework for Efficient Code Optimization","created":"2023-12-09","cited_by_count":8,"area":null},{"id":"2407.02518","title":"INDICT: Code Generation with Internal Dialogues of Critiques for Both Security and Helpfulness","created":"2024-06-23","cited_by_count":8,"area":null},{"id":"2408.02976","title":"Empathy Level Alignment via Reinforcement Learning for Empathetic Response Generation","created":"2024-08-06","cited_by_count":8,"area":null},{"id":"2512.13472","title":"Scaling Laws for Code: Every Programming Language Matters","created":"2025-12-15","cited_by_count":8,"area":null},{"id":"2601.20679","title":"ShieldedCode: Learning Robust Representations for Virtual Machine Protected Code","created":"2026-01-28","cited_by_count":8,"area":null},{"id":"2603.15611","title":"Code-A1: Adversarial Evolving of Code LLM and Test LLM via Reinforcement Learning","created":"2026-03-16","cited_by_count":8,"area":null},{"id":"2401.07870","title":"JumpCoder: Go Beyond Autoregressive Coder via Online Modification","created":"2024-01-15","cited_by_count":7,"area":null},{"id":"2410.15489","title":"Generative AI Agents in Autonomous Machines: A Safety Perspective","created":"2024-10-20","cited_by_count":7,"area":null},{"id":"2411.14503","title":"Planning-Driven Programming: A Large Language Model Programming Workflow","created":"2024-11-21","cited_by_count":7,"area":null},{"id":"2508.05242","title":"CodeBoost: Boosting Code LLMs by Squeezing Knowledge from Code Snippets with RL","created":"2025-08-07","cited_by_count":7,"area":null},{"id":"2509.05208","title":"Symbolic Graphics Programming with Large Language Models","created":"2025-09-05","cited_by_count":7,"area":null},{"id":"2510.06824","title":"Efficient numeracy in language models through single-token number embeddings","created":"2025-10-08","cited_by_count":7,"area":null},{"id":"2603.03072","title":"TikZilla: Scaling Text-to-TikZ with High-Quality Data and Reinforcement Learning","created":"2026-03-03","cited_by_count":7,"area":null},{"id":"2411.05199","title":"CodeLutra: Boosting LLM Code Generation via Preference-Guided Refinement","created":"2024-11-07","cited_by_count":6,"area":null},{"id":"2505.11480","title":"SuperCoder: Assembly Program Superoptimization with Large Language Models","created":"2025-05-16","cited_by_count":6,"area":null},{"id":"2603.29847","title":"CADReasoner: Iterative Program Editing for CAD Reverse Engineering","created":"2026-02-18","cited_by_count":6,"area":null},{"id":"2604.18995","title":"$R^2$-dLLM: Accelerating Diffusion Large Language Models via Spatio-Temporal Redundancy Reduction","created":"2026-04-21","cited_by_count":6,"area":null},{"id":"2305.10091","title":"Multi-Agent Reinforcement Learning: Methods, Applications, Visionary Prospects, and Challenges","created":"2023-05-17","cited_by_count":5,"area":null},{"id":"2507.06968","title":"Scaling Towards the Information Boundary of Instruction Sets: The Infinity Instruct Subject Technical Report","created":"2025-07-09","cited_by_count":5,"area":null},{"id":"2509.17730","title":"ConfClip: Confidence-Weighted and Clipped Reward for Reinforcement Learning in LLMs","created":"2025-09-22","cited_by_count":5,"area":null},{"id":"2601.12186","title":"Aletheia: What Makes RLVR For Code Verifiers Tick?","created":"2026-01-17","cited_by_count":5,"area":null},{"id":"2601.19494","title":"AACR-Bench: Evaluating Automatic Code Review with Holistic Repository-Level Context","created":"2026-01-27","cited_by_count":5,"area":null},{"id":"2604.10508","title":"How Many Tries Does It Take? Iterative Self-Repair in LLM Code Generation Across Model Scales and Benchmarks","created":"2026-04-12","cited_by_count":5,"area":null},{"id":"2303.05378","title":"Greener yet Powerful: Taming Large Code Generation Models with Quantization","created":"2023-03-09","cited_by_count":4,"area":null},{"id":"2309.13218","title":"Language Models for Business Optimisation with a Real World Case Study in Production Scheduling","created":"2023-09-22","cited_by_count":4,"area":null},{"id":"2401.08089","title":"A Study on Training and Developing Large Language Models for Behavior Tree Generation","created":"2024-01-16","cited_by_count":4,"area":null},{"id":"2409.00571","title":"Enhancing Source Code Security with LLMs: Demystifying The Challenges and Generating Reliable Repairs","created":"2024-09-01","cited_by_count":4,"area":null},{"id":"2412.08859","title":"ViUniT: Visual Unit Tests for More Robust Visual Programming","created":"2024-12-12","cited_by_count":4,"area":null},{"id":"2412.13464","title":"GenX: Mastering Code and Test Generation with Execution Feedback","created":"2024-12-18","cited_by_count":4,"area":null},{"id":"2504.00019","title":"ObscuraCoder: Powering Efficient Code LM Pre-Training Via Obfuscation Grounding","created":"2025-03-27","cited_by_count":4,"area":null}],"next_cursor":"100"}