{"total":133,"rows":[{"id":"2305.01210","title":"Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation","created":"2023-05-02","cited_by_count":1391,"area":null},{"id":"2407.01489","title":"Agentless: Demystifying LLM-based Software Engineering Agents","created":"2024-07-01","cited_by_count":421,"area":"agents"},{"id":"2308.10620","title":"Large Language Models for Software Engineering: A Systematic Literature Review","created":"2023-08-21","cited_by_count":399,"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":"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":"2312.02120","title":"Magicoder: Empowering Code Generation with OSS-Instruct","created":"2023-12-04","cited_by_count":256,"area":null},{"id":"2403.17134","title":"RepairAgent: An Autonomous, LLM-Based Agent for Program Repair","created":"2024-03-25","cited_by_count":232,"area":"agents"},{"id":"2409.02977","title":"Large Language Model-Based Agents for Software Engineering: A Survey","created":"2024-09-04","cited_by_count":178,"area":"agents"},{"id":"2403.17927","title":"MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution","created":"2024-03-26","cited_by_count":134,"area":"agents"},{"id":"2404.00971","title":"Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Code","created":"2024-04-01","cited_by_count":107,"area":null},{"id":"2506.11791","title":"SEC-bench: Automated Benchmarking of LLM Agents on Real-World Software Security Tasks","created":"2025-06-13","cited_by_count":75,"area":"agents"},{"id":"2409.00899","title":"MarsCode Agent: AI-native Automated Bug Fixing","created":"2024-09-02","cited_by_count":71,"area":"agents"},{"id":"2404.14662","title":"NExT: Teaching Large Language Models to Reason about Code Execution","created":"2024-04-23","cited_by_count":63,"area":"lr"},{"id":"2410.24198","title":"SelfCodeAlign: Self-Alignment for Code Generation","created":"2024-10-31","cited_by_count":62,"area":null},{"id":"2504.04030","title":"OpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMs","created":"2025-04-05","cited_by_count":60,"area":null},{"id":"2501.08200","title":"CWEval: Outcome-driven Evaluation on Functionality and Security of LLM Code Generation","created":"2025-01-14","cited_by_count":59,"area":null},{"id":"2404.14646","title":"Exploring and Unleashing the Power of Large Language Models in Automated Code Translation","created":"2024-04-23","cited_by_count":57,"area":null},{"id":"2309.00608","title":"Copiloting the Copilots: Fusing Large Language Models with Completion Engines for Automated Program Repair","created":"2023-09-01","cited_by_count":55,"area":null},{"id":"2309.07062","title":"Large Language Models for Compiler Optimization","created":"2023-09-11","cited_by_count":52,"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":"2310.01152","title":"Large Language Model-Powered Smart Contract Vulnerability Detection: New Perspectives","created":"2023-10-02","cited_by_count":48,"area":null},{"id":"2410.01215","title":"From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging","created":"2024-10-02","cited_by_count":46,"area":null},{"id":"2305.14752","title":"A New Era in Software Security: Towards Self-Healing Software via Large Language Models and Formal Verification","created":"2023-05-24","cited_by_count":42,"area":null},{"id":"2307.10236","title":"Look Before You Leap: An Exploratory Study of Uncertainty Measurement for Large Language Models","created":"2023-07-16","cited_by_count":41,"area":null},{"id":"2403.19114","title":"Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM","created":"2024-03-28","cited_by_count":40,"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":"2406.06822","title":"An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection","created":"2024-06-10","cited_by_count":40,"area":"safety"},{"id":"2407.02524","title":"Meta Large Language Model Compiler: Foundation Models of Compiler Optimization","created":"2024-06-27","cited_by_count":39,"area":null},{"id":"2502.06215","title":"LessLeak-Bench: A First Investigation of Data Leakage in LLMs Across 83 Software Engineering Benchmarks","created":"2025-02-10","cited_by_count":37,"area":null},{"id":"2606.06324","title":"From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flaws","created":"2026-06-04","cited_by_count":29,"area":"agents"},{"id":"2308.10462","title":"Exploring Parameter-Efficient Fine-Tuning Techniques for Code Generation with Large Language Models","created":"2023-08-21","cited_by_count":28,"area":null},{"id":"2408.12159","title":"Search-Based LLMs for Code Optimization","created":"2024-08-22","cited_by_count":28,"area":null},{"id":"2503.09002","title":"KNighter: Transforming Static Analysis with LLM-Synthesized Checkers","created":"2025-03-12","cited_by_count":24,"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":"2311.06530","title":"Exploring ChatGPT's Capabilities on Vulnerability Management","created":"2023-11-11","cited_by_count":19,"area":null},{"id":"2405.04520","title":"NaturalCodeBench: Examining Coding Performance Mismatch on HumanEval and Natural User Prompts","created":"2024-05-07","cited_by_count":19,"area":null},{"id":"2509.01835","title":"From CVE Entries to Verifiable Exploits: An Automated Multi-Agent Framework for Reproducing CVEs","created":"2025-09-01","cited_by_count":18,"area":"agents"},{"id":"2305.14699","title":"Can Transformers Learn to Solve Problems Recursively?","created":"2023-05-24","cited_by_count":17,"area":null},{"id":"2401.00563","title":"KernelGPT: Enhanced Kernel Fuzzing via Large Language Models","created":"2023-12-31","cited_by_count":17,"area":null},{"id":"2308.07655","title":"From Commit Message Generation to History-Aware Commit Message Completion","created":"2023-08-15","cited_by_count":16,"area":null},{"id":"2405.15130","title":"OptLLM: Optimal Assignment of Queries to Large Language Models","created":"2024-05-24","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":"2402.06598","title":"CigaR: Cost-efficient Program Repair with LLMs","created":"2024-02-09","cited_by_count":15,"area":null},{"id":"2606.28434","title":"SWE-MeM: Learning Adaptive Memory Management for Long-Horizon Coding Agents","created":"2026-06-26","cited_by_count":15,"area":"agents"},{"id":"2401.12947","title":"Transformer-Based Models Are Not Yet Perfect At Learning to Emulate Structural Recursion","created":"2024-01-23","cited_by_count":14,"area":null},{"id":"2408.02487","title":"LiCoEval: Evaluating LLMs on License Compliance in Code Generation","created":"2024-08-05","cited_by_count":14,"area":null},{"id":"2410.09997","title":"Collu-Bench: A Benchmark for Predicting Language Model Hallucinations in Code","created":"2024-10-13","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":"2404.08877","title":"Aligning the Objective of LLM-based Program Repair","created":"2024-04-13","cited_by_count":12,"area":null},{"id":"2405.16792","title":"Laurel: Unblocking Automated Verification with Large Language Models","created":"2024-05-27","cited_by_count":11,"area":null},{"id":"2406.11589","title":"CoSQA+: Pioneering the Multi-Choice Code Search Benchmark with Test-Driven Agents","created":"2024-06-17","cited_by_count":11,"area":"agents"},{"id":"2605.26563","title":"TrajAudit: Automated Failure Diagnosis for Agentic Coding Systems","created":"2026-05-26","cited_by_count":11,"area":"agents"},{"id":"2401.03741","title":"Enhanced Automated Code Vulnerability Repair using Large Language Models","created":"2024-01-08","cited_by_count":10,"area":null},{"id":"2408.03519","title":"RepoMasterEval: Evaluating Code Completion via Real-World Repositories","created":"2024-08-07","cited_by_count":10,"area":null},{"id":"2409.15204","title":"RAMBO: Enhancing RAG-based Repository-Level Method Body Completion","created":"2024-09-23","cited_by_count":10,"area":null},{"id":"2312.14856","title":"Turbulence: Systematically and Automatically Testing Instruction-Tuned Large Language Models for Code","created":"2023-12-22","cited_by_count":9,"area":null},{"id":"2403.14714","title":"Compiler generated feedback for Large Language Models","created":"2024-03-18","cited_by_count":9,"area":null},{"id":"2402.18734","title":"Priority Sampling of Large Language Models for Compilers","created":"2024-02-28","cited_by_count":8,"area":null},{"id":"2508.19506","title":"Learning Game-Playing Agents with Generative Code Optimization","created":"2025-08-27","cited_by_count":8,"area":"agents"},{"id":"2303.10494","title":"Revisiting the Plastic Surgery Hypothesis via Large Language Models","created":"2023-03-18","cited_by_count":7,"area":null},{"id":"2409.10033","title":"Can GPT-O1 Kill All Bugs? An Evaluation of GPT-Family LLMs on QuixBugs","created":"2024-09-16","cited_by_count":7,"area":null},{"id":"2505.02931","title":"The Art of Repair: Optimizing Iterative Program Repair with Instruction-Tuned Models","created":"2025-05-05","cited_by_count":7,"area":null},{"id":"2605.12913","title":"Revisiting DAgger in the Era of LLM-Agents","created":"2026-05-13","cited_by_count":7,"area":"agents"},{"id":"2307.00012","title":"FlakyFix: Using Large Language Models for Predicting Flaky Test Fix Categories and Test Code Repair","created":"2023-06-21","cited_by_count":6,"area":null},{"id":"2312.05275","title":"Exploring the Limits of ChatGPT in Software Security Applications","created":"2023-12-08","cited_by_count":6,"area":null},{"id":"2408.04660","title":"XMainframe: A Large Language Model for Mainframe Modernization","created":"2024-08-05","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":"2507.18755","title":"Agentic Program Repair from Test Failures at Scale: A Neuro-symbolic approach with static analysis and test execution feedback","created":"2025-07-24","cited_by_count":6,"area":"agents"},{"id":"2309.12938","title":"Frustrated with Code Quality Issues? LLMs can Help!","created":"2023-09-22","cited_by_count":5,"area":null},{"id":"2312.05356","title":"Neuron Patching: Semantic-based Neuron-level Language Model Repair for Code Generation","created":"2023-12-08","cited_by_count":5,"area":null},{"id":"2502.00519","title":"CoDocBench: A Dataset for Code-Documentation Alignment in Software Maintenance","created":"2025-02-01","cited_by_count":5,"area":null},{"id":"2604.01527","title":"REAP: Automatic Curation of Coding Agent Benchmarks from Interactive Production Usage","created":"2026-04-02","cited_by_count":5,"area":"agents"},{"id":"2604.13120","title":"AgentForge: Execution-Grounded Multi-Agent LLM Framework for Autonomous Software Engineering","created":"2026-04-13","cited_by_count":5,"area":"agents"},{"id":"2310.09690","title":"Configuration Validation with Large Language Models","created":"2023-10-15","cited_by_count":4,"area":null},{"id":"2310.14211","title":"LUNA: A Model-Based Universal Analysis Framework for Large Language Models","created":"2023-10-22","cited_by_count":4,"area":null},{"id":"2505.17703","title":"Gradient-Based Program Repair: Fixing Bugs in Continuous Program Spaces","created":"2025-05-23","cited_by_count":4,"area":null},{"id":"2508.00459","title":"Thinking Machines: Mathematical Reasoning in the Age of LLMs","created":"2025-08-01","cited_by_count":4,"area":"lr"},{"id":"2508.02611","title":"Meta-RAG on Large Codebases Using Code Summarization","created":"2025-08-04","cited_by_count":4,"area":null},{"id":"2510.03463","title":"ALMAS: an Autonomous LLM-based Multi-Agent Software Engineering Framework","created":"2025-10-03","cited_by_count":4,"area":"agents"},{"id":"2602.11000","title":"Fine-Tuning GPT-5 for GPU Kernel Generation","created":"2026-02-11","cited_by_count":4,"area":null},{"id":"2607.06273","title":"AgentTether: Graph-Guided Diagnosis and Runtime Intervention for Reliable LLM Agent Operation","created":"2026-07-07","cited_by_count":4,"area":"agents"},{"id":"2401.07518","title":"Survey of Natural Language Processing for Education: Taxonomy, Systematic Review, and Future Trends","created":"2024-01-15","cited_by_count":3,"area":null},{"id":"2401.07994","title":"Assessing the Latent Automated Program Repair Capabilities of Large Language Models using Round-Trip Translation","created":"2024-01-15","cited_by_count":3,"area":null},{"id":"2502.17441","title":"Renaissance of Literate Programming in the Era of LLMs: Enhancing LLM-Based Code Generation in Large-Scale Projects","created":"2024-12-25","cited_by_count":3,"area":null},{"id":"2503.09217","title":"Evaluating the Generalizability of LLMs in Automated Program Repair","created":"2025-03-12","cited_by_count":3,"area":null},{"id":"2506.01374","title":"REASONING COMPILER: LLM-Guided Optimizations for Efficient Model Serving","created":"2025-06-02","cited_by_count":3,"area":"lr"},{"id":"2507.19909","title":"The Impact of Fine-tuning Large Language Models on Automated Program Repair","created":"2025-07-26","cited_by_count":3,"area":null},{"id":"2509.07571","title":"Towards Generalized Routing: Model and Agent Orchestration for Adaptive and Efficient Inference","created":"2025-09-09","cited_by_count":3,"area":"agents"},{"id":"2512.14018","title":"PerfCoder: Large Language Models for Interpretable Code Performance Optimization","created":"2025-12-16","cited_by_count":3,"area":null},{"id":"2604.16335","title":"Beyond Verifiable Rewards: Rubric-Based GRM for Reinforced Fine-Tuning SWE Agents","created":"2026-03-13","cited_by_count":3,"area":"agents"},{"id":"2605.04903","title":"Delta-Based Neural Architecture Search: LLM Fine-Tuning via Code Diffs","created":"2026-05-06","cited_by_count":3,"area":null},{"id":"2605.28557","title":"Token Optimization Strategies for LLM-Based Oracle-to-PostgreSQL Migration","created":"2026-05-27","cited_by_count":3,"area":null},{"id":"2607.19843","title":"Beyond Fail-to-Pass: Iterative Hardening of Co-Generated Bug Reproduction Tests and Fixes","created":"2026-07-22","cited_by_count":3,"area":null},{"id":"2404.09384","title":"Generative transformations and patterns in LLM-native approaches for software verification and falsification","created":"2024-04-14","cited_by_count":2,"area":null},{"id":"2410.09117","title":"REDO: Execution-Free Runtime Error Detection for COding Agents","created":"2024-10-10","cited_by_count":2,"area":"agents"},{"id":"2411.10842","title":"CODECLEANER: Elevating Standards with A Robust Data Contamination Mitigation Toolkit","created":"2024-11-16","cited_by_count":2,"area":null},{"id":"2505.18220","title":"Navigating Pitfalls: Evaluating LLMs in Machine Learning Programming Education","created":"2025-05-23","cited_by_count":2,"area":null},{"id":"2507.15157","title":"Can LLMs Generate User Stories and Assess Their Quality?","created":"2025-07-20","cited_by_count":2,"area":null},{"id":"2602.06090","title":"SVRepair: Structured Visual Reasoning for Automated Program Repair","created":"2026-02-05","cited_by_count":2,"area":"lr"},{"id":"2603.03683","title":"CONCUR: Benchmarking LLMs for Concurrent Code Generation","created":"2026-03-04","cited_by_count":2,"area":null}],"next_cursor":"100"}