{"total":114,"rows":[{"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":"2402.19473","title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","created":"2024-02-29","cited_by_count":354,"area":"rag"},{"id":"2401.03065","title":"CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution","created":"2024-01-05","cited_by_count":300,"area":null},{"id":"2404.05427","title":"AutoCodeRover: Autonomous Program Improvement","created":"2024-04-08","cited_by_count":278,"area":null},{"id":"2402.16906","title":"Debug like a Human: A Large Language Model Debugger via Verifying Runtime Execution Step-by-step","created":"2024-02-25","cited_by_count":127,"area":null},{"id":"2303.10868","title":"Retrieving Multimodal Information for Augmented Generation: A Survey","created":"2023-03-20","cited_by_count":85,"area":null},{"id":"2405.03644","title":"When LLMs Meet Cybersecurity: A Systematic Literature Review","created":"2024-05-06","cited_by_count":71,"area":null},{"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":"2410.24198","title":"SelfCodeAlign: Self-Alignment for Code Generation","created":"2024-10-31","cited_by_count":62,"area":null},{"id":"2403.08937","title":"Bugs in Large Language Models Generated Code: An Empirical Study","created":"2024-03-13","cited_by_count":60,"area":null},{"id":"2601.16443","title":"Endless Terminals: Scaling RL Environments for Terminal Agents","created":"2026-01-23","cited_by_count":54,"area":"synth"},{"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":"2312.12450","title":"Can It Edit? Evaluating the Ability of Large Language Models to Follow Code Editing Instructions","created":"2023-12-11","cited_by_count":48,"area":null},{"id":"2405.19358","title":"Robustifying Safety-Aligned Large Language Models through Clean Data Curation","created":"2024-05-24","cited_by_count":44,"area":"alignment"},{"id":"2306.02907","title":"SelfEvolve: A Code Evolution Framework via Large Language Models","created":"2023-06-05","cited_by_count":43,"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":"2412.21199","title":"HumanEval Pro and MBPP Pro: Evaluating Large Language Models on Self-invoking Code Generation","created":"2024-12-30","cited_by_count":39,"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":"2405.11430","title":"MHPP: Exploring the Capabilities and Limitations of Language Models Beyond Basic Code Generation","created":"2024-05-19","cited_by_count":26,"area":null},{"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":"2406.07737","title":"The Future of AI-Driven Software Engineering","created":"2024-06-11","cited_by_count":23,"area":null},{"id":"2510.04905","title":"Retrieval-Augmented Code Generation: A Survey with Focus on Repository-Level Approaches","created":"2025-10-06","cited_by_count":23,"area":"rag"},{"id":"2602.02361","title":"SWE-Universe: Scale Real-World Verifiable Environments to Millions","created":"2026-02-02","cited_by_count":19,"area":null},{"id":"2405.11706","title":"Increasing the LLM Accuracy for Question Answering: Ontologies to the Rescue!","created":"2024-05-20","cited_by_count":18,"area":null},{"id":"2402.03907","title":"Embedding Large Language Models into Extended Reality: Opportunities and Challenges for Inclusion, Engagement, and Privacy","created":"2024-02-06","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":"2404.08877","title":"Aligning the Objective of LLM-based Program Repair","created":"2024-04-13","cited_by_count":12,"area":null},{"id":"2405.20519","title":"Diffusion On Syntax Trees For Program Synthesis","created":"2024-05-30","cited_by_count":10,"area":"diffusion"},{"id":"2503.09433","title":"CASTLE: Benchmarking Dataset for Static Code Analyzers and LLMs towards CWE Detection","created":"2025-03-12","cited_by_count":10,"area":null},{"id":"2505.21069","title":"CXXCrafter: An LLM-Based Agent for Automated C/C++ Open Source Software Building","created":"2025-05-27","cited_by_count":10,"area":"agents"},{"id":"2502.14202","title":"Do LLMs Consider Security? An Empirical Study on Responses to Programming Questions","created":"2025-02-20","cited_by_count":9,"area":null},{"id":"2402.10691","title":"Python is Not Always the Best Choice: Embracing Multilingual Program of Thoughts","created":"2024-02-16","cited_by_count":8,"area":"lr"},{"id":"2405.14906","title":"AutoCoder: Enhancing Code Large Language Model with \\textsc{AIEV-Instruct}","created":"2024-05-23","cited_by_count":8,"area":null},{"id":"2504.20964","title":"OSVBench: Benchmarking LLMs on Specification Generation Tasks for Operating System Verification","created":"2025-04-29","cited_by_count":8,"area":null},{"id":"2508.14066","title":"Retrieval-Augmented Generation in Industry: An Interview Study on Use Cases, Requirements, Challenges, and Evaluation","created":"2025-08-11","cited_by_count":8,"area":"rag"},{"id":"2411.03471","title":"MetRex: A Benchmark for Verilog Code Metric Reasoning Using LLMs","created":"2024-11-05","cited_by_count":7,"area":"lr"},{"id":"2312.05275","title":"Exploring the Limits of ChatGPT in Software Security Applications","created":"2023-12-08","cited_by_count":6,"area":null},{"id":"2404.08885","title":"Is Next Token Prediction Sufficient for GPT? Exploration on Code Logic Comprehension","created":"2024-04-13","cited_by_count":6,"area":null},{"id":"2412.14841","title":"Helping LLMs Improve Code Generation Using Feedback from Testing and Static Analysis","created":"2024-12-19","cited_by_count":6,"area":null},{"id":"2412.18989","title":"How Propense Are Large Language Models at Producing Code Smells? A Benchmarking Study","created":"2024-12-25","cited_by_count":6,"area":null},{"id":"2506.11591","title":"Retrieval-Augmented Code Review Comment Generation","created":"2025-06-13","cited_by_count":6,"area":"rag"},{"id":"2309.12938","title":"Frustrated with Code Quality Issues? LLMs can Help!","created":"2023-09-22","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":"2501.07058","title":"Logic Meets Magic: LLMs Cracking Smart Contract Vulnerabilities","created":"2025-01-13","cited_by_count":5,"area":null},{"id":"2503.12205","title":"PredicateFix: Repairing Static Analysis Alerts with Bridging Predicates","created":"2025-03-15","cited_by_count":5,"area":"rag"},{"id":"2508.05970","title":"Impact-driven Context Filtering For Cross-file Code Completion","created":"2025-08-08","cited_by_count":5,"area":"rag"},{"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":"2409.10959","title":"Leveraging Reviewer Experience in Code Review Comment Generation","created":"2024-09-17","cited_by_count":4,"area":null},{"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":"2412.19031","title":"Repository Structure-Aware Training Makes SLMs Better Issue Resolver","created":"2024-12-26","cited_by_count":4,"area":null},{"id":"2505.15356","title":"NL-Debugging: Exploiting Natural Language as an Intermediate Representation for Code Debugging","created":"2025-05-21","cited_by_count":4,"area":null},{"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":"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":"2603.05744","title":"CodeScout: Contextual Problem Statement Enhancement for Software Agents","created":"2026-03-05","cited_by_count":4,"area":"agents"},{"id":"2405.13932","title":"Chain of Targeted Verification Questions to Improve the Reliability of Code Generated by LLMs","created":"2024-05-22","cited_by_count":3,"area":null},{"id":"2407.21227","title":"TaskEval: Assessing Difficulty of Code Generation Tasks for Large Language Models","created":"2024-07-30","cited_by_count":3,"area":null},{"id":"2409.11190","title":"SuperCoder2.0: Technical Report on Exploring the feasibility of LLMs as Autonomous Programmer","created":"2024-09-17","cited_by_count":3,"area":"rag"},{"id":"2410.02220","title":"Data to Defense: The Role of Curation in Customizing LLMs Against Jailbreaking Attacks","created":"2024-10-03","cited_by_count":3,"area":"safety"},{"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":"2503.22512","title":"Unlocking LLM Repair Capabilities Through Cross-Language Translation and Multi-Agent Refinement","created":"2025-03-28","cited_by_count":3,"area":"agents"},{"id":"2506.07239","title":"VeriLoC: Line-of-Code Level Prediction of Hardware Design Quality from Verilog Code","created":"2025-06-08","cited_by_count":3,"area":null},{"id":"2512.14018","title":"PerfCoder: Large Language Models for Interpretable Code Performance Optimization","created":"2025-12-16","cited_by_count":3,"area":null},{"id":"2601.19726","title":"RvB: Automating AI System Hardening via Iterative Red-Blue Games","created":"2026-01-27","cited_by_count":3,"area":"safety"},{"id":"2607.04574","title":"A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training","created":"2026-07-06","cited_by_count":3,"area":"agents"},{"id":"2309.14760","title":"Program Repair with Minimal Edits Using CodeT5","created":"2023-09-26","cited_by_count":2,"area":null},{"id":"2405.01559","title":"Untangling Knots: Leveraging LLM for Error Resolution in Computational Notebooks","created":"2024-03-26","cited_by_count":2,"area":null},{"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":"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":"2502.11901","title":"Building A Proof-Oriented Programmer That Is 64% Better Than GPT-4o Under Data Scarcity","created":"2025-02-17","cited_by_count":2,"area":"lr"},{"id":"2502.12203","title":"An Interpretable Automated Mechanism Design Framework with Large Language Models","created":"2025-02-16","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":"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":"2510.07189","title":"Secure-Instruct: An Automated Pipeline for Synthesizing Instruction-Tuning Datasets Using LLMs for Secure Code Generation","created":"2025-10-08","cited_by_count":2,"area":"synth"},{"id":"2511.00488","title":"\\texttt{ReMind}: Understanding Deductive Code Reasoning in LLMs","created":"2025-11-01","cited_by_count":2,"area":"lr"},{"id":"2604.17338","title":"Precise Debugging Benchmark: Is Your Model Debugging or Regenerating?","created":"2026-04-19","cited_by_count":2,"area":null},{"id":"2607.01867","title":"An Exploratory Study on LLM-Generated Code and Comments in Code Repositories","created":"2026-07-02","cited_by_count":2,"area":null},{"id":"2312.01656","title":"The Contemporary Art of Image Search: Iterative User Intent Expansion via Vision-Language Model","created":"2023-12-04","cited_by_count":1,"area":"mllm"},{"id":"2312.10448","title":"Exploring Large Language Models in Resolving Environment-Related Crash Bugs: Localizing and Repairing","created":"2023-12-16","cited_by_count":1,"area":null},{"id":"2501.18005","title":"Fault Localization via Fine-tuning Large Language Models with Mutation Generated Stack Traces","created":"2025-01-29","cited_by_count":1,"area":null},{"id":"2502.01273","title":"Analysis of Student-LLM Interaction in a Software Engineering Project","created":"2025-02-03","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":"2504.07027","title":"Using ML filters to help automated vulnerability repairs: when it helps and when it doesn't","created":"2025-04-09","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":"2506.01770","title":"ReGA: Model-Based Safeguard for LLMs via Representation-Guided Abstraction","created":"2025-06-02","cited_by_count":1,"area":"safety"},{"id":"2511.03925","title":"Collaborative Agents for Automated Program Repair in Ruby","created":"2025-11-06","cited_by_count":1,"area":"agents"},{"id":"2511.21380","title":"Multi-Agent Systems for Dataset Adaptation in Software Engineering: Capabilities, Limitations, and Future Directions","created":"2025-11-26","cited_by_count":1,"area":"agents"},{"id":"2603.13384","title":"VulnAgent-R2: Evidence-Calibrated Multi-Agent Auditing for Repository-Level Vulnerability Detection","created":"2026-03-11","cited_by_count":1,"area":"agents"},{"id":"2604.08293","title":"CIAO - Code In Architecture Out - Automated Software Architecture Documentation with Large Language Models","created":"2026-04-09","cited_by_count":1,"area":null},{"id":"2607.02520","title":"AutoResearch: An Execution-Grounded Multi-Agent Framework for Reliable Research Workflow Automation","created":"2026-05-04","cited_by_count":1,"area":"agents"},{"id":"2608.14065","title":"Rethinking Automated Program Repair: The Impact of Bug Complexity, Fault Localization, and LLM Cost-efficiency","created":"2026-08-14","cited_by_count":1,"area":null},{"id":"2404.06082","title":"A RAG Method for Source Code Inquiry Tailored to Long-Context LLMs","created":"2024-04-09","cited_by_count":0,"area":"rag"},{"id":"2404.15681","title":"Automated Creation of Source Code Variants of a Cryptographic Hash Function Implementation Using Generative Pre-Trained Transformer Models","created":"2024-04-24","cited_by_count":0,"area":null},{"id":"2412.13467","title":"Transducer Tuning: Efficient Model Adaptation for Software Tasks Using Code Property Graphs","created":"2024-12-18","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":"2507.03047","title":"Enhancing Temporal Sensitivity of Large Language Model for Recommendation with Counterfactual Tuning","created":"2025-07-03","cited_by_count":0,"area":"lr"},{"id":"2507.13629","title":"Large Language Models in Cybersecurity: Applications, Vulnerabilities, and Defense Techniques","created":"2025-07-18","cited_by_count":0,"area":null},{"id":"2508.02840","title":"Resource-Efficient Automatic Software Vulnerability Assessment via Knowledge Distillation and Particle Swarm Optimization","created":"2025-07-30","cited_by_count":0,"area":"distill"},{"id":"2508.10701","title":"REFN: A Reinforcement-Learning-From-Network Framework against 1-day/n-day Exploitations","created":"2025-08-14","cited_by_count":0,"area":null}],"next_cursor":"100"}