{"list":"other","total":54,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2308.11432","title":"A Survey on Large Language Model based Autonomous Agents","created":"2023-08-22","cited_by_count":2242},{"id":"2310.11511","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","created":"2023-10-17","cited_by_count":1839},{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601},{"id":"2407.16741","title":"OpenHands: An Open Platform for AI Software Developers as Generalist Agents","created":"2024-07-23","cited_by_count":1002},{"id":"2308.10620","title":"Large Language Models for Software Engineering: A Systematic Literature Review","created":"2023-08-21","cited_by_count":399},{"id":"2401.11817","title":"Hallucination is Inevitable: An Innate Limitation of Large Language Models","created":"2024-01-22","cited_by_count":332},{"id":"2407.01502","title":"AI Agents That Matter","created":"2024-07-01","cited_by_count":219},{"id":"2407.19354","title":"The Emerged Security and Privacy of LLM Agent: A Survey with Case Studies","created":"2024-07-28","cited_by_count":131},{"id":"2209.11515","title":"Large Language Models are Few-shot Testers: Exploring LLM-based General Bug Reproduction","created":"2022-09-23","cited_by_count":111},{"id":"2502.13172","title":"Unveiling Privacy Risks in LLM Agent Memory","created":"2025-02-17","cited_by_count":101},{"id":"2409.20550","title":"LLM Hallucinations in Practical Code Generation: Phenomena, Mechanism, and Mitigation","created":"2024-09-30","cited_by_count":93},{"id":"2504.17550","title":"HalluLens: LLM Hallucination Benchmark","created":"2025-04-24","cited_by_count":92},{"id":"1810.05995","title":"BLEU is Not Suitable for the Evaluation of Text Simplification","created":"2018-10-14","cited_by_count":78},{"id":"2310.01726","title":"Large Language Models for Test-Free Fault Localization","created":"2023-10-03","cited_by_count":67},{"id":"2409.09030","title":"Agents in Software Engineering: Survey, Landscape, and Vision","created":"2024-09-13","cited_by_count":60},{"id":"2504.11281","title":"The Obvious Invisible Threat: LLM-Powered GUI Agents' Vulnerability to Fine-Print Injections","created":"2025-04-15","cited_by_count":59},{"id":"2308.05487","title":"A Quantitative and Qualitative Evaluation of LLM-Based Explainable Fault Localization","created":"2023-08-10","cited_by_count":50},{"id":"2510.06265","title":"Large Language Models Hallucination: A Comprehensive Survey","created":"2025-10-05","cited_by_count":49},{"id":"2304.02195","title":"Explainable Automated Debugging via Large Language Model-driven Scientific Debugging","created":"2023-04-05","cited_by_count":40},{"id":"2406.04531","title":"TESTEVAL: Benchmarking Large Language Models for Test Case Generation","created":"2024-06-06","cited_by_count":40},{"id":"1801.10269","title":"The Impact of Class Rebalancing Techniques on the Performance and Interpretation of Defect Prediction Models","created":"2018-01-31","cited_by_count":29},{"id":"2505.24019","title":"LLM Agents Should Employ Security Principles","created":"2025-05-29","cited_by_count":29},{"id":"2404.13340","title":"Large Language Models as Test Case Generators: Performance Evaluation and Enhancement","created":"2024-04-20","cited_by_count":28},{"id":"2504.21030","title":"Advancing Multi-Agent Systems Through Model Context Protocol: Architecture, Implementation, and Applications","created":"2025-04-26","cited_by_count":23},{"id":"2502.01821","title":"Agentic Bug Reproduction for Effective Automated Program Repair at Google","created":"2025-02-03","cited_by_count":22},{"id":"2506.14683","title":"Unified Software Engineering Agent as AI Software Engineer","created":"2025-06-17","cited_by_count":19},{"id":"1608.07754","title":"Precise Condition Synthesis for Program Repair","created":"2016-08-28","cited_by_count":13},{"id":"1906.07107","title":"Assessing the Quality of the Steps to Reproduce in Bug Reports","created":"2019-06-17","cited_by_count":13},{"id":"2311.04532","title":"Evaluating Diverse Large Language Models for Automatic and General Bug Reproduction","created":"2023-11-08","cited_by_count":12},{"id":"2301.01113","title":"Invalidator: Automated Patch Correctness Assessment via Semantic and Syntactic Reasoning","created":"2023-01-03","cited_by_count":11},{"id":"2411.01414","title":"A Deep Dive Into Large Language Model Code Generation Mistakes: What and Why?","created":"2024-11-03","cited_by_count":10},{"id":"2502.02009","title":"LLMSecConfig: An LLM-Based Approach for Fixing Software Container Misconfigurations","created":"2025-02-04","cited_by_count":9},{"id":"2407.05165","title":"Feedback-Driven Automated Whole Bug Report Reproduction for Android Apps","created":"2024-07-06","cited_by_count":7},{"id":"1704.04769","title":"Automatic Bug Triage using Semi-Supervised Text Classification","created":"2017-04-16","cited_by_count":6},{"id":"2401.03069","title":"Towards Enhancing the Reproducibility of Deep Learning Bugs: An Empirical Study","created":"2024-01-05","cited_by_count":6},{"id":"2402.15943","title":"Rethinking Software Engineering in the Foundation Model Era: A Curated Catalogue of Challenges in the Development of Trustworthy FMware","created":"2024-02-25","cited_by_count":6},{"id":"2302.06050","title":"BURT: A Chatbot for Interactive Bug Reporting","created":"2023-02-13","cited_by_count":5},{"id":"2405.10845","title":"Natural Language Processing for Requirements Traceability","created":"2024-05-17","cited_by_count":5},{"id":"1804.02433","title":"Traceability in the Wild: Automatically Augmenting Incomplete Trace Links","created":"2018-04-06","cited_by_count":4},{"id":"2204.09368","title":"BugListener: Identifying and Synthesizing Bug Reports from Collaborative Live Chats","created":"2022-04-20","cited_by_count":4},{"id":"2209.10062","title":"Toward Interactive Bug Reporting for (Android App) End-Users","created":"2022-09-21","cited_by_count":4},{"id":"2502.15099","title":"An Empirical Study on Leveraging Images in Automated Bug Report Reproduction","created":"2025-02-20","cited_by_count":4},{"id":"2503.20036","title":"Agents in the Sandbox: End-to-End Crash Bug Reproduction for Minecraft","created":"2025-03-25","cited_by_count":4},{"id":"2504.18804","title":"Can We Enhance Bug Report Quality Using LLMs?: An Empirical Study of LLM-Based Bug Report Generation","created":"2025-04-26","cited_by_count":3},{"id":"2507.04422","title":"Learning Software Bug Reports: A Systematic Literature Review","created":"2025-07-06","cited_by_count":3},{"id":"2502.04251","title":"Combining Language and App UI Analysis for the Automated Assessment of Bug Reproduction Steps","created":"2025-02-06","cited_by_count":2},{"id":"2506.16440","title":"Evaluating the Use of LLMs for Documentation to Code Traceability","created":"2025-06-19","cited_by_count":2},{"id":"2309.03044","title":"Method-Level Bug Severity Prediction using Source Code Metrics and LLMs","created":"2023-09-06","cited_by_count":1}],"next_cursor":null}