{"total":76,"rows":[{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373,"area":null},{"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":"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":"2409.02977","title":"Large Language Model-Based Agents for Software Engineering: A Survey","created":"2024-09-04","cited_by_count":178,"area":"agents"},{"id":"2304.00385","title":"Keep the Conversation Going: Fixing 162 out of 337 bugs for $0.42 each using ChatGPT","created":"2023-04-01","cited_by_count":125,"area":null},{"id":"2511.13646","title":"Live-SWE-agent: Can Software Engineering Agents Self-Evolve on the Fly?","created":"2025-11-17","cited_by_count":95,"area":"agents"},{"id":"2405.04760","title":"Large Language Models for Cyber Security: A Systematic Literature Review","created":"2024-05-08","cited_by_count":68,"area":null},{"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":"2504.04030","title":"OpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMs","created":"2025-04-05","cited_by_count":60,"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":"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":"2309.07062","title":"Large Language Models for Compiler Optimization","created":"2023-09-11","cited_by_count":52,"area":null},{"id":"2312.15698","title":"RepairLLaMA: Efficient Representations and Fine-Tuned Adapters for Program Repair","created":"2023-12-25","cited_by_count":50,"area":null},{"id":"2303.03004","title":"xCodeEval: A Large Scale Multilingual Multitask Benchmark for Code Understanding, Generation, Translation and Retrieval","created":"2023-03-06","cited_by_count":47,"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":"2301.13246","title":"Conversational Automated Program Repair","created":"2023-01-30","cited_by_count":41,"area":null},{"id":"2408.08313","title":"Can Large Language Models Understand Symbolic Graphics Programs?","created":"2024-08-15","cited_by_count":35,"area":null},{"id":"2501.07531","title":"Evaluating Agent-based Program Repair at Google","created":"2025-01-13","cited_by_count":35,"area":"agents"},{"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":"2209.14876","title":"Repairing Bugs in Python Assignments Using Large Language Models","created":"2022-09-29","cited_by_count":28,"area":null},{"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":"2406.07737","title":"The Future of AI-Driven Software Engineering","created":"2024-06-11","cited_by_count":23,"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":"2412.06294","title":"Beyond pip install: Evaluating LLM Agents for the Automated Installation of Python Projects","created":"2024-12-09","cited_by_count":21,"area":"agents"},{"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":"2401.10314","title":"LangProp: A code optimization framework using Large Language Models applied to driving","created":"2024-01-18","cited_by_count":18,"area":"driving"},{"id":"2304.12015","title":"ITER: Iterative Neural Repair for Multi-Location Patches","created":"2023-04-24","cited_by_count":16,"area":null},{"id":"2402.00093","title":"ChIRAAG: ChatGPT Informed Rapid and Automated Assertion Generation","created":"2024-01-31","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":"2304.03816","title":"Towards Generating Functionally Correct Code Edits from Natural Language Issue Descriptions","created":"2023-04-07","cited_by_count":14,"area":null},{"id":"2306.17077","title":"RAPGen: An Approach for Fixing Code Inefficiencies in Zero-Shot","created":"2023-06-29","cited_by_count":14,"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":"2301.01113","title":"Invalidator: Automated Patch Correctness Assessment via Semantic and Syntactic Reasoning","created":"2023-01-03","cited_by_count":11,"area":null},{"id":"2212.11414","title":"Improving Automated Program Repair with Domain Adaptation","created":"2022-12-21","cited_by_count":10,"area":null},{"id":"2409.18952","title":"RepairBench: Leaderboard of Frontier Models for Program Repair","created":"2024-09-27","cited_by_count":9,"area":null},{"id":"2505.20749","title":"Can Agents Fix Agent Issues?","created":"2025-05-27","cited_by_count":9,"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":"2409.19894","title":"TransAgent: Enhancing LLM-Based Code Translation via Fine-Grained Execution Alignment","created":"2024-09-30","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":"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":"2408.04660","title":"XMainframe: A Large Language Model for Mainframe Modernization","created":"2024-08-05","cited_by_count":6,"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":"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":"2210.05506","title":"Follow-up Attention: An Empirical Study of Developer and Neural Model Code Exploration","created":"2022-10-11","cited_by_count":5,"area":null},{"id":"2404.19336","title":"Improving LLM Classification of Logical Errors by Integrating Error Relationship into Prompts","created":"2024-04-30","cited_by_count":5,"area":null},{"id":"2410.16655","title":"Memory-Efficient Large Language Models for Program Repair with Semantic-Guided Patch Generation","created":"2024-10-22","cited_by_count":5,"area":null},{"id":"2305.13884","title":"Multi-Granularity Detector for Vulnerability Fixes","created":"2023-05-23","cited_by_count":4,"area":null},{"id":"2411.15442","title":"Automatic High-quality Verilog Assertion Generation through Subtask-Focused Fine-Tuned LLMs and Iterative Prompting","created":"2024-11-23","cited_by_count":4,"area":null},{"id":"2504.20412","title":"kAgent: An execution-guided crash resolution agent for the Linux kernel","created":"2025-04-29","cited_by_count":4,"area":"agents"},{"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":"2402.12222","title":"CovRL: Fuzzing JavaScript Engines with Coverage-Guided Reinforcement Learning for LLM-based Mutation","created":"2024-02-19","cited_by_count":3,"area":null},{"id":"2502.18487","title":"AuPair: Golden Example Pairs for Code Repair","created":"2025-02-12","cited_by_count":3,"area":"lr"},{"id":"2503.09217","title":"Evaluating the Generalizability of LLMs in Automated Program Repair","created":"2025-03-12","cited_by_count":3,"area":null},{"id":"2503.22512","title":"Unlocking LLM Repair Capabilities Through Cross-Language Translation and Multi-Agent Refinement","created":"2025-03-28","cited_by_count":3,"area":"agents"},{"id":"2504.02141","title":"On Simulation-Guided LLM-based Code Generation for Safe Autonomous Driving Software","created":"2025-04-02","cited_by_count":3,"area":"driving"},{"id":"2410.20136","title":"CodePurify: Defend Backdoor Attacks on Neural Code Models via Entropy-based Purification","created":"2024-10-26","cited_by_count":2,"area":"safety"},{"id":"2501.12339","title":"Treefix: Enabling Execution with a Tree of Prefixes","created":"2025-01-21","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},{"id":"2407.14540","title":"Risks of ignoring uncertainty propagation in AI-augmented security pipelines","created":"2024-07-14","cited_by_count":1,"area":null},{"id":"2409.05177","title":"Insights from Benchmarking Frontier Language Models on Web App Code Generation","created":"2024-09-08","cited_by_count":1,"area":null},{"id":"2410.18893","title":"Creating and Repairing Robot Programs in Open-World Domains","created":"2024-10-24","cited_by_count":1,"area":null},{"id":"2507.10103","title":"Accelerating Automatic Program Repair with Dual Retrieval-Augmented Fine-Tuning and Patch Generation on Large Language Models","created":"2025-07-14","cited_by_count":1,"area":"rag"},{"id":"2509.06052","title":"Empirical Study of Code Large Language Models for Binary Security Patch Detection","created":"2025-09-07","cited_by_count":1,"area":null},{"id":"2605.17535","title":"AgentModernize: Preserving Business Logic in Legacy Modernization with Multi-Agent LLMs and Behavioral Specification Graphs","created":"2026-05-17","cited_by_count":1,"area":"agents"},{"id":"2606.26979","title":"How Much Static Structure Do Code Agents Need? A Study of Deterministic Anchoring","created":"2026-06-25","cited_by_count":1,"area":"agents"},{"id":"2607.12605","title":"Multi-Perspective Agentic Program Repair via Code Property Graphs and Temporal Execution Graphs","created":"2026-07-14","cited_by_count":1,"area":"agents"},{"id":"2308.05014","title":"A Comprehensive Empirical Study of Bugs in Open-Source Federated Learning Frameworks","created":"2023-08-09","cited_by_count":0,"area":null},{"id":"2505.07372","title":"Self-Bootstrapping Automated Program Repair: Using LLMs to Generate and Evaluate Synthetic Training Data for Bug Repair","created":"2025-05-12","cited_by_count":0,"area":"synth"},{"id":"2506.21211","title":"$T^3$: Multi-level Tree-based Automatic Program Repair with Large Language Models","created":"2025-06-26","cited_by_count":0,"area":"lr"},{"id":"2604.12108","title":"LLM-Based Automated Diagnosis Of Integration Test Failures At Google","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2604.17464","title":"Project Prometheus: Bridging the Intent Gap in Agentic Program Repair via Reverse-Engineered Executable Specifications","created":"2026-04-19","cited_by_count":0,"area":"agents"},{"id":"2608.04611","title":"The Order Is the Guarantee: Verifier-Budgeted Code Deletion with Static-First Learned Proposals","created":"2026-08-05","cited_by_count":0,"area":null}],"next_cursor":null}