{"total":125,"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":"2406.15877","title":"BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions","created":"2024-06-22","cited_by_count":546,"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":"2312.02003","title":"A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly","created":"2023-12-04","cited_by_count":387,"area":null},{"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":"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":"2308.04748","title":"Fuzz4All: Universal Fuzzing with Large Language Models","created":"2023-08-09","cited_by_count":88,"area":null},{"id":"2308.03314","title":"GPTScan: Detecting Logic Vulnerabilities in Smart Contracts by Combining GPT with Program Analysis","created":"2023-08-07","cited_by_count":65,"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":"2512.18470","title":"SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios","created":"2025-12-20","cited_by_count":59,"area":"agents"},{"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":"2509.23586","title":"Reducing Cost of LLM Agents with Trajectory Reduction","created":"2025-09-28","cited_by_count":48,"area":"agents"},{"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":"2408.05534","title":"Can LLMs Replace Manual Annotation of Software Engineering Artifacts?","created":"2024-08-10","cited_by_count":42,"area":null},{"id":"2405.02580","title":"PropertyGPT: LLM-driven Formal Verification of Smart Contracts through Retrieval-Augmented Property Generation","created":"2024-05-04","cited_by_count":37,"area":"rag"},{"id":"2404.17153","title":"UniDebugger: Hierarchical Multi-Agent Framework for Unified Software Debugging","created":"2024-04-26","cited_by_count":35,"area":"agents"},{"id":"2501.07531","title":"Evaluating Agent-based Program Repair at Google","created":"2025-01-13","cited_by_count":35,"area":"agents"},{"id":"2408.13001","title":"CRUXEval-X: A Benchmark for Multilingual Code Reasoning, Understanding and Execution","created":"2024-08-23","cited_by_count":31,"area":"lr"},{"id":"2404.18353","title":"How secure is AI-generated Code: A Large-Scale Comparison of Large Language Models","created":"2024-04-29","cited_by_count":24,"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":"2407.07472","title":"Rectifier: Code Translation with Corrector via LLMs","created":"2024-07-10","cited_by_count":20,"area":null},{"id":"2502.10931","title":"D-CIPHER: Dynamic Collaborative Intelligent Multi-Agent System with Planner and Heterogeneous Executors for Offensive Security","created":"2025-02-15","cited_by_count":20,"area":"agents"},{"id":"2508.13143","title":"Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks","created":"2025-08-18","cited_by_count":20,"area":"agents"},{"id":"2305.12138","title":"Exploring Code Analysis: Zero-Shot Insights on Syntax and Semantics with LLMs","created":"2023-05-20","cited_by_count":19,"area":null},{"id":"2309.04142","title":"Trustworthy and Synergistic Artificial Intelligence for Software Engineering: Vision and Roadmaps","created":"2023-09-08","cited_by_count":19,"area":null},{"id":"2308.00245","title":"The Hitchhiker's Guide to Program Analysis: A Journey with Large Language Models","created":"2023-08-01","cited_by_count":18,"area":null},{"id":"2310.05046","title":"FakeGPT: Fake News Generation, Explanation and Detection of Large Language Models","created":"2023-10-08","cited_by_count":17,"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":"2509.13941","title":"An Empirical Study on Failures in Automated Issue Solving","created":"2025-09-17","cited_by_count":16,"area":"agents"},{"id":"2402.06598","title":"CigaR: Cost-efficient Program Repair with LLMs","created":"2024-02-09","cited_by_count":15,"area":null},{"id":"2511.18538","title":"From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence","created":"2025-11-23","cited_by_count":15,"area":"agents"},{"id":"2503.12374","title":"Beyond Final Code: A Process-Oriented Error Analysis of Software Development Agents in Real-World GitHub Scenarios","created":"2025-03-16","cited_by_count":14,"area":"agents"},{"id":"2505.17107","title":"CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution","created":"2025-05-21","cited_by_count":14,"area":"agents"},{"id":"2310.19813","title":"Enhancing Genetic Improvement Mutations Using Large Language Models","created":"2023-10-18","cited_by_count":13,"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":"2404.04306","title":"AuditGPT: Auditing Smart Contracts with ChatGPT","created":"2024-04-05","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":"2408.12056","title":"Enhancing Automated Program Repair with Solution Design","created":"2024-08-22","cited_by_count":8,"area":null},{"id":"2506.17208","title":"Dissecting the SWE-Bench Leaderboards: Profiling Submitters and Architectures of LLM- and Agent-Based Repair Systems","created":"2025-06-20","cited_by_count":8,"area":"agents"},{"id":"2601.09822","title":"LLM-Based Agentic Systems for Software Engineering: Challenges and Opportunities","created":"2026-01-14","cited_by_count":8,"area":"agents"},{"id":"2309.10419","title":"Learning from Teaching Assistants to Program with Subgoals: Exploring the Potential for AI Teaching Assistants","created":"2023-09-19","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":"2509.13755","title":"Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning","created":"2025-09-17","cited_by_count":7,"area":"safety"},{"id":"2312.05275","title":"Exploring the Limits of ChatGPT in Software Security Applications","created":"2023-12-08","cited_by_count":6,"area":null},{"id":"2411.15501","title":"Instruct or Interact? Exploring and Eliciting LLMs' Capability in Code Snippet Adaptation Through Prompt Engineering","created":"2024-11-23","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":"2508.07468","title":"CP-Agent: Agentic Constraint Programming","created":"2025-08-10","cited_by_count":6,"area":"agents"},{"id":"2512.22256","title":"Agentic Software Issue Resolution with Large Language Models: A Survey","created":"2025-12-24","cited_by_count":6,"area":"agents"},{"id":"2605.07509","title":"MASPrism: Lightweight Failure Attribution for Multi-Agent Systems Using Prefill-Stage Signals","created":"2026-05-08","cited_by_count":6,"area":"agents"},{"id":"2403.16347","title":"ChatGPT Incorrectness Detection in Software Reviews","created":"2024-03-25","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":"2510.26457","title":"SecureReviewer: Enhancing Large Language Models for Secure Code Review through Secure-aware Fine-tuning","created":"2025-10-30","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":"2410.06176","title":"SC-Bench: A Large-Scale Dataset for Smart Contract Auditing","created":"2024-10-08","cited_by_count":4,"area":null},{"id":"2504.15284","title":"EditLord: Learning Code Transformation Rules for Code Editing","created":"2025-03-10","cited_by_count":4,"area":null},{"id":"2505.04852","title":"Raw Pointer Rewriting with LLMs for Translating C to Safer Rust","created":"2025-05-07","cited_by_count":4,"area":null},{"id":"2510.07740","title":"AppForge: From Assistant to Independent Developer -- Are GPTs Ready for Software Development?","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2605.08717","title":"Debugging the Debuggers: Failure-Anchored Structured Recovery for Software Engineering Agents","created":"2026-05-09","cited_by_count":4,"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":"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":"2512.14018","title":"PerfCoder: Large Language Models for Interpretable Code Performance Optimization","created":"2025-12-16","cited_by_count":3,"area":null},{"id":"2512.24635","title":"DynaFix: Iterative Automated Program Repair Driven by Execution-Level Dynamic Information","created":"2025-12-31","cited_by_count":3,"area":null},{"id":"2603.08718","title":"CktEvo: Repository-Level RTL Code Benchmark for Design Evolution","created":"2026-02-10","cited_by_count":3,"area":null},{"id":"2604.03758","title":"AutoReSpec: A Framework for Generating Specification using Large Language Models","created":"2026-04-04","cited_by_count":3,"area":null},{"id":"2608.16801","title":"When Agents Coordinate: Measuring Coordination in Multi-Agent AI Coding","created":"2026-08-17","cited_by_count":3,"area":"agents"},{"id":"2408.15658","title":"An Empirical Study on Self-correcting Large Language Models for Data Science Code Generation","created":"2024-08-28","cited_by_count":2,"area":null},{"id":"2501.12339","title":"Treefix: Enabling Execution with a Tree of Prefixes","created":"2025-01-21","cited_by_count":2,"area":null},{"id":"2501.12617","title":"Deep Learning-Based Identification of Inconsistent Method Names: How Far Are We?","created":"2025-01-22","cited_by_count":2,"area":null},{"id":"2504.17198","title":"Automatically Generating Rules of Malicious Software Packages via Large Language Model","created":"2025-04-24","cited_by_count":2,"area":null},{"id":"2507.15822","title":"Do AI models help produce verified bug fixes?","created":"2025-07-21","cited_by_count":2,"area":null},{"id":"2509.25203","title":"Generating High-Quality Datasets for Code Editing via Open-Source Language Models","created":"2025-09-19","cited_by_count":2,"area":null},{"id":"2601.13933","title":"VulnResolver: A Hybrid Agent Framework for LLM-Based Automated Vulnerability Issue Resolution","created":"2026-01-20","cited_by_count":2,"area":"agents"},{"id":"2603.17826","title":"FailureMem: A Failure-Aware Multimodal Framework for Autonomous Software Repair","created":"2026-03-18","cited_by_count":2,"area":null},{"id":"2604.17338","title":"Precise Debugging Benchmark: Is Your Model Debugging or Regenerating?","created":"2026-04-19","cited_by_count":2,"area":null},{"id":"2605.30105","title":"EvoRepair: Enhancing Vulnerability Repair Agents Through Experience-Based Self-Evolution","created":"2026-05-28","cited_by_count":2,"area":"agents"},{"id":"2606.22110","title":"TraceView: Interactive Visualization of Agentic Program Repair Trajectories","created":"2026-06-20","cited_by_count":2,"area":"agents"},{"id":"2310.12425","title":"Automated Repair of Declarative Software Specifications in the Era of Large Language Models","created":"2023-10-19","cited_by_count":1,"area":null},{"id":"2406.16739","title":"Agent-Driven Automatic Software Improvement","created":"2024-06-24","cited_by_count":1,"area":"agents"},{"id":"2408.08619","title":"PatUntrack: Automated Generating Patch Examples for Issue Reports without Tracked Insecure Code","created":"2024-08-16","cited_by_count":1,"area":null},{"id":"2410.04485","title":"Exploring the Potential of Conversational Test Suite Based Program Repair on SWE-bench","created":"2024-10-06","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":"2504.15637","title":"DR.FIX: Automatically Fixing Data Races at Industry Scale","created":"2025-04-22","cited_by_count":1,"area":null},{"id":"2506.13182","title":"From Empirical Evaluation to Context-Aware Enhancement: Repairing Regression Errors with LLMs","created":"2025-06-16","cited_by_count":1,"area":null},{"id":"2507.20109","title":"Learning to Align Human Code Preferences","created":"2025-07-27","cited_by_count":1,"area":"alignment"},{"id":"2509.23835","title":"HFuzzer: Testing Large Language Models for Package Hallucinations via Phrase-based Fuzzing","created":"2025-09-28","cited_by_count":1,"area":null},{"id":"2510.16059","title":"SIADAFIX: issue description response for adaptive program repair","created":"2025-10-17","cited_by_count":1,"area":"lr"},{"id":"2511.03925","title":"Collaborative Agents for Automated Program Repair in Ruby","created":"2025-11-06","cited_by_count":1,"area":"agents"},{"id":"2601.04540","title":"AdaptEval: A Benchmark for Evaluating Large Language Models on Code Snippet Adaptation","created":"2026-01-08","cited_by_count":1,"area":null},{"id":"2603.09004","title":"Can AI Agents Generate Microservices? How Far are We?","created":"2026-03-09","cited_by_count":1,"area":"agents"},{"id":"2603.27333","title":"ComBench: A Repo-level Real-world Benchmark for Compilation Error Repair","created":"2026-03-28","cited_by_count":1,"area":null},{"id":"2604.24212","title":"Empowering Autonomous Debugging Agents with Efficient Dynamic Analysis","created":"2026-04-27","cited_by_count":1,"area":"agents"},{"id":"2604.24218","title":"RefEvo: Agentic Design with Co-Evolutionary Verification for Agile Reference Model Generation","created":"2026-04-27","cited_by_count":1,"area":"agents"},{"id":"2605.00382","title":"Social Bias in LLM-Generated Code: Benchmark and Mitigation","created":"2026-05-01","cited_by_count":1,"area":null},{"id":"2605.09134","title":"BoostAPR: Boosting Automated Program Repair via Execution-Grounded Reinforcement Learning with Dual Reward Models","created":"2026-05-09","cited_by_count":1,"area":"alignment"},{"id":"2605.16725","title":"Baba in Wonderland: Online Self-Supervised Dynamics Discovery for Executable World Models","created":"2026-05-16","cited_by_count":1,"area":"wm"}],"next_cursor":"100"}