{"total":111,"rows":[{"id":"2308.11432","title":"A Survey on Large Language Model based Autonomous Agents","created":"2023-08-22","cited_by_count":2242,"area":"agents"},{"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":"2403.17134","title":"RepairAgent: An Autonomous, LLM-Based Agent for Program Repair","created":"2024-03-25","cited_by_count":232,"area":"agents"},{"id":"2308.01861","title":"ClassEval: A Manually-Crafted Benchmark for Evaluating LLMs on Class-level Code Generation","created":"2023-08-03","cited_by_count":168,"area":null},{"id":"2406.12952","title":"SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents","created":"2024-06-18","cited_by_count":133,"area":"agents"},{"id":"2408.02479","title":"From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Future","created":"2024-08-05","cited_by_count":86,"area":"agents"},{"id":"2401.00812","title":"If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agents","created":"2024-01-01","cited_by_count":79,"area":"agents"},{"id":"2303.16749","title":"Improving Code Generation by Training with Natural Language Feedback","created":"2023-03-28","cited_by_count":76,"area":null},{"id":"2304.06815","title":"Automatic Semantic Augmentation of Language Model Prompts (for Code Summarization)","created":"2023-04-13","cited_by_count":72,"area":null},{"id":"2509.14745","title":"On the Use of Agentic Coding: An Empirical Study of Pull Requests on GitHub","created":"2025-09-18","cited_by_count":55,"area":"agents"},{"id":"2308.03656","title":"Emotionally Numb or Empathetic? Evaluating How LLMs Feel Using EmotionBench","created":"2023-08-07","cited_by_count":54,"area":null},{"id":"2309.14345","title":"Bias Testing and Mitigation in LLM-based Code Generation","created":"2023-09-03","cited_by_count":53,"area":null},{"id":"2308.01240","title":"Evaluating Instruction-Tuned Large Language Models on Code Comprehension and Generation","created":"2023-08-02","cited_by_count":50,"area":null},{"id":"2412.10133","title":"You Name It, I Run It: An LLM Agent to Execute Tests of Arbitrary Projects","created":"2024-12-13","cited_by_count":47,"area":"agents"},{"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":"2405.18649","title":"LeDex: Training LLMs to Better Self-Debug and Explain Code","created":"2024-05-28","cited_by_count":40,"area":null},{"id":"2403.15852","title":"SOEN-101: Code Generation by Emulating Software Process Models Using Large Language Model Agents","created":"2024-03-23","cited_by_count":34,"area":"agents"},{"id":"2404.04442","title":"Exploring Autonomous Agents through the Lens of Large Language Models: A Review","created":"2024-04-05","cited_by_count":31,"area":"agents"},{"id":"2404.13340","title":"Large Language Models as Test Case Generators: Performance Evaluation and Enhancement","created":"2024-04-20","cited_by_count":28,"area":null},{"id":"2502.05368","title":"Otter: Generating Tests from Issues to Validate SWE Patches","created":"2025-02-07","cited_by_count":25,"area":null},{"id":"2409.17647","title":"MECD: Unlocking Multi-Event Causal Discovery in Video Reasoning","created":"2024-09-26","cited_by_count":23,"area":"lr"},{"id":"2501.17167","title":"QualityFlow: An Agentic Workflow for Program Synthesis Controlled by LLM Quality Checks","created":"2025-01-20","cited_by_count":22,"area":"agents"},{"id":"2502.01821","title":"Agentic Bug Reproduction for Effective Automated Program Repair at Google","created":"2025-02-03","cited_by_count":22,"area":"agents"},{"id":"2306.05153","title":"Is AI the better programming partner? Human-Human Pair Programming vs. Human-AI pAIr Programming","created":"2023-06-08","cited_by_count":20,"area":null},{"id":"2210.03696","title":"LLMEffiChecker: Understanding and Testing Efficiency Degradation of Large Language Models","created":"2022-10-07","cited_by_count":16,"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":"2506.08311","title":"Understanding Automated Program Repair Agents Through the Lens of Traceability: An Empirical Study","created":"2025-06-10","cited_by_count":16,"area":"agents"},{"id":"2311.08649","title":"Autonomous Large Language Model Agents Enabling Intent-Driven Mobile GUI Testing","created":"2023-11-15","cited_by_count":15,"area":"agents"},{"id":"2502.06111","title":"CSR-Bench: Benchmarking LLM Agents in Deployment of Computer Science Research Repositories","created":"2025-02-10","cited_by_count":15,"area":"agents"},{"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":"2502.10802","title":"CoCoEvo: Co-Evolution of Programs and Test Cases to Enhance Code Generation","created":"2025-02-15","cited_by_count":14,"area":null},{"id":"2306.05152","title":"Towards Autonomous Testing Agents via Conversational Large Language Models","created":"2023-06-08","cited_by_count":13,"area":"agents"},{"id":"2509.16736","title":"Towards Transparent and Incentive-Compatible Collaboration in Decentralized LLM Multi-Agent Systems: A Blockchain-Driven Approach","created":"2025-09-20","cited_by_count":12,"area":"agents"},{"id":"2402.15100","title":"Studying LLM Performance on Closed- and Open-source Data","created":"2024-02-23","cited_by_count":11,"area":null},{"id":"2507.10540","title":"FusionFactory: Fusing LLM Capabilities with Multi-LLM Log Data","created":"2025-07-14","cited_by_count":10,"area":null},{"id":"2409.10741","title":"NaviQAte: Functionality-Guided Web Application Navigation","created":"2024-09-16","cited_by_count":9,"area":null},{"id":"2309.09980","title":"Code Representation Pre-training with Complements from Program Executions","created":"2023-09-04","cited_by_count":8,"area":null},{"id":"2408.07846","title":"A System for Automated Unit Test Generation Using Large Language Models and Assessment of Generated Test Suites","created":"2024-08-14","cited_by_count":8,"area":null},{"id":"2503.00481","title":"Challenges in Testing Large Language Model Based Software: A Faceted Taxonomy","created":"2025-03-01","cited_by_count":8,"area":"agents"},{"id":"2603.23613","title":"LLMLOOP: Improving LLM-Generated Code and Tests through Automated Iterative Feedback Loops","created":"2026-03-24","cited_by_count":8,"area":null},{"id":"2310.07856","title":"Assessing Evaluation Metrics for Neural Test Oracle Generation","created":"2023-10-11","cited_by_count":7,"area":null},{"id":"2409.12682","title":"Retrieval-Augmented Test Generation: How Far Are We?","created":"2024-09-19","cited_by_count":7,"area":"rag"},{"id":"2504.18050","title":"Validating Network Protocol Parsers with Traceable RFC Document Interpretation","created":"2025-04-25","cited_by_count":7,"area":null},{"id":"2511.16004","title":"InfCode: Adversarial Iterative Refinement of Tests and Patches for Reliable Software Issue Resolution","created":"2025-11-20","cited_by_count":7,"area":null},{"id":"2309.06578","title":"Can Large Language Models Discern Evidence for Scientific Hypotheses? Case Studies in the Social Sciences","created":"2023-09-07","cited_by_count":6,"area":null},{"id":"2401.16310","title":"An Insight into Security Code Review with LLMs: Capabilities, Obstacles, and Influential Factors","created":"2024-01-29","cited_by_count":6,"area":"lr"},{"id":"2501.11086","title":"Evaluating LLM-Based Regression Test Generation","created":"2025-01-19","cited_by_count":6,"area":null},{"id":"2510.03588","title":"REFINE: Enhancing Program Repair Agents through Context-Aware Patch Refinement","created":"2025-10-04","cited_by_count":6,"area":"agents"},{"id":"2510.23761","title":"TDFlow: Agentic Workflows for Test Driven Development","created":"2025-10-27","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":"2601.19066","title":"Dynamic Cogeneration of Bug Reproduction Test in Agentic Program Repair","created":"2026-01-27","cited_by_count":6,"area":"agents"},{"id":"2504.13515","title":"Large Language Models for Validating Network Protocol Parsers","created":"2025-04-18","cited_by_count":5,"area":null},{"id":"2512.21132","title":"AutoBaxBuilder: Bootstrapping Code Security Benchmarking","created":"2025-12-24","cited_by_count":5,"area":"synth"},{"id":"2607.00990","title":"SWE-Doctor: Guiding Software Engineering Agents with Runtime Diagnosis from Multi-Faceted Bug Reproduction Tests","created":"2026-07-01","cited_by_count":5,"area":"agents"},{"id":"2312.04687","title":"LLM4TDD: Best Practices for Test Driven Development Using Large Language Models","created":"2023-12-07","cited_by_count":4,"area":null},{"id":"2401.08138","title":"LLMs for Test Input Generation for Semantic Caches","created":"2024-01-16","cited_by_count":4,"area":null},{"id":"2405.00066","title":"Research and application of artificial intelligence based webshell detection model: A literature review","created":"2024-04-28","cited_by_count":4,"area":null},{"id":"2407.08597","title":"Learning Program Behavioral Models from Synthesized Input-Output Pairs","created":"2024-07-11","cited_by_count":4,"area":null},{"id":"2411.16927","title":"ASSERTIFY: Utilizing Large Language Models to Generate Assertions for Production Code","created":"2024-11-25","cited_by_count":4,"area":null},{"id":"2503.20036","title":"Agents in the Sandbox: End-to-End Crash Bug Reproduction for Minecraft","created":"2025-03-25","cited_by_count":4,"area":"agents"},{"id":"2504.12608","title":"Code Copycat Conundrum: Demystifying Repetition in LLM-based Code Generation","created":"2025-04-17","cited_by_count":4,"area":null},{"id":"2510.08005","title":"Past, Present, and Future of Bug Tracking in the Generative AI Era","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2601.13713","title":"SWE-Tester: Training Open-Source LLMs for Issue Reproduction in Real-World Repositories","created":"2026-01-20","cited_by_count":4,"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":"2609.09133","title":"ExecCritic: Learn to Test, Test to Improve for Coding Agents","created":"2026-09-08","cited_by_count":3,"area":"agents"},{"id":"2402.07408","title":"Large Language Models are Few-shot Generators: Proposing Hybrid Prompt Algorithm To Generate Webshell Escape Samples","created":"2024-02-12","cited_by_count":2,"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":"2409.06416","title":"Exploring the Integration of Large Language Models in Industrial Test Maintenance Processes","created":"2024-09-10","cited_by_count":2,"area":null},{"id":"2412.06684","title":"Exploring Critical Testing Scenarios for Decision-Making Policies: An LLM Approach","created":"2024-12-09","cited_by_count":2,"area":null},{"id":"2506.03590","title":"VCDiag: Classifying Erroneous Waveforms for Failure Triage Acceleration","created":"2025-06-04","cited_by_count":2,"area":null},{"id":"2507.22065","title":"Fuzzing: Randomness? Reasoning! Efficient Directed Fuzzing via Large Language Models","created":"2025-06-30","cited_by_count":2,"area":"lr"},{"id":"2509.25043","title":"Large Language Models for Software Testing: A Research Roadmap","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2511.00052","title":"Feature-Guided Analysis of Neural Networks: A Replication Study","created":"2025-10-28","cited_by_count":2,"area":null},{"id":"2512.23844","title":"From Correctness to Collaboration: Toward a Human-Centered Framework for Evaluating AI Agent Behavior in Software Engineering","created":"2025-12-29","cited_by_count":2,"area":"agents"},{"id":"2601.13097","title":"RM -RF: Reward Model for Run-Free Unit Test Evaluation","created":"2026-01-19","cited_by_count":2,"area":null},{"id":"2406.17790","title":"Mashee at SemEval-2024 Task 8: The Impact of Samples Quality on the Performance of In-Context Learning for Machine Text Classification","created":"2024-05-28","cited_by_count":1,"area":null},{"id":"2409.01382","title":"Automatic Detection of LLM-Generated Code: A Comparative Case Study of Contemporary Models Across Function and Class Granularities","created":"2024-09-02","cited_by_count":1,"area":null},{"id":"2503.03951","title":"WIP: Assessing the Effectiveness of ChatGPT in Preparatory Testing Activities","created":"2025-03-05","cited_by_count":1,"area":null},{"id":"2507.22414","title":"AutoCodeSherpa: Symbolic Explanations in AI Coding Agents","created":"2025-07-30","cited_by_count":1,"area":"agents"},{"id":"2507.23336","title":"DSBC : Data Science task Benchmarking with Context engineering","created":"2025-07-31","cited_by_count":1,"area":"agents"},{"id":"2508.19472","title":"SIExVulTS: Sensitive Information Exposure Vulnerability Detection System using Transformer Models and Static Analysis","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2512.14990","title":"Imitation Game: Reproducing Deep Learning Bugs Leveraging an Intelligent Agent","created":"2025-12-17","cited_by_count":1,"area":"agents"},{"id":"2601.23009","title":"SolAgent: A Specialized Multi-Agent Framework for Solidity Code Generation","created":"2026-01-30","cited_by_count":1,"area":"agents"},{"id":"2602.13723","title":"Compiling Large Multi-Modal Requirement Documents into Runnable Software Systems: From an Agentic Test-Driven Perspective","created":"2026-02-14","cited_by_count":1,"area":"agents"},{"id":"2604.24212","title":"Empowering Autonomous Debugging Agents with Efficient Dynamic Analysis","created":"2026-04-27","cited_by_count":1,"area":"agents"},{"id":"2605.15229","title":"PBT-Bench: Benchmarking AI Agents on Property-Based Testing","created":"2026-05-13","cited_by_count":1,"area":"agents"},{"id":"2607.08983","title":"SCATE: Learning to Supervise Coding Agents for Cost-Effective Test Generation","created":"2026-07-09","cited_by_count":1,"area":"agents"},{"id":"2607.09123","title":"ReProAgent: Tool-Augmented Multi-Stage Agentic Generation of Bug Reproduction Tests from Issue Reports","created":"2026-07-10","cited_by_count":1,"area":"agents"},{"id":"2608.06811","title":"Coupling Planning with Episodic Memory in LLM Agents for Software Issue Resolution","created":"2026-08-07","cited_by_count":1,"area":"agents"},{"id":"2610.01023","title":"Groundability, Not Scale Alone: When Weak Reviewers Can Audit Strong Coding Agents","created":"2026-10-01","cited_by_count":1,"area":"agents"},{"id":"2410.18107","title":"In-Context Code-Text Learning for Bimodal Software Engineering","created":"2024-10-08","cited_by_count":0,"area":null},{"id":"2504.21045","title":"Leveraging LLM to Strengthen ML-Based Cross-Site Scripting Detection","created":"2025-04-28","cited_by_count":0,"area":null},{"id":"2506.11559","title":"Leveraging GPT-4 for Vulnerability-Witnessing Unit Test Generation","created":"2025-06-13","cited_by_count":0,"area":null},{"id":"2508.04125","title":"Experimental Analysis of Productive Interaction Strategy with ChatGPT: User Study on Function and Project-level Code Generation Tasks","created":"2025-08-06","cited_by_count":0,"area":null},{"id":"2511.03934","title":"PEFA-AI: Advancing Open-source LLMs for RTL generation using Progressive Error Feedback Agentic-AI","created":"2025-11-06","cited_by_count":0,"area":"agents"},{"id":"2512.00325","title":"Progressive Code Integration for Abstractive Bug Report Summarization","created":"2025-11-29","cited_by_count":0,"area":null},{"id":"2601.02045","title":"The New Compiler Stack: A Survey on the Synergy of LLMs and Compilers","created":"2026-01-05","cited_by_count":0,"area":null},{"id":"2601.02602","title":"SWaRL: Safeguard Code Watermarking via Reinforcement Learning","created":"2026-01-05","cited_by_count":0,"area":null},{"id":"2601.18241","title":"TAM-Eval: Evaluating LLMs for Automated Unit Test Maintenance","created":"2026-01-26","cited_by_count":0,"area":null}],"next_cursor":"100"}