{"total":71,"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":"2308.10620","title":"Large Language Models for Software Engineering: A Systematic Literature Review","created":"2023-08-21","cited_by_count":399,"area":null},{"id":"2507.23370","title":"Trae Agent: An LLM-based Agent for Software Engineering with Test-time Scaling","created":"2025-07-31","cited_by_count":94,"area":"lr"},{"id":"2404.09491","title":"Large Language Models Can Automatically Engineer Features for Few-Shot Tabular Learning","created":"2024-04-15","cited_by_count":81,"area":null},{"id":"2304.11938","title":"Is ChatGPT the Ultimate Programming Assistant -- How far is it?","created":"2023-04-24","cited_by_count":76,"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":"2403.08937","title":"Bugs in Large Language Models Generated Code: An Empirical Study","created":"2024-03-13","cited_by_count":60,"area":null},{"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":"2405.17503","title":"Code Repair with LLMs gives an Exploration-Exploitation Tradeoff","created":"2024-05-26","cited_by_count":51,"area":null},{"id":"2402.02047","title":"Calibration and Correctness of Language Models for Code","created":"2024-02-03","cited_by_count":49,"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":"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":"2406.06822","title":"An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection","created":"2024-06-10","cited_by_count":40,"area":"safety"},{"id":"2302.04662","title":"Generating High-Precision Feedback for Programming Syntax Errors using Large Language Models","created":"2023-01-24","cited_by_count":34,"area":null},{"id":"2304.10423","title":"Fully Autonomous Programming with Large Language Models","created":"2023-04-20","cited_by_count":31,"area":null},{"id":"2508.11126","title":"AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunities","created":"2025-08-15","cited_by_count":28,"area":"agents"},{"id":"2402.01386","title":"Can Large Language Models Serve as Data Analysts? A Multi-Agent Assisted Approach for Qualitative Data Analysis","created":"2024-02-02","cited_by_count":20,"area":"agents"},{"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":"2410.12468","title":"Evaluating Software Development Agents: Patch Patterns, Code Quality, and Issue Complexity in Real-World GitHub Scenarios","created":"2024-10-16","cited_by_count":18,"area":"agents"},{"id":"2304.12015","title":"ITER: Iterative Neural Repair for Multi-Location Patches","created":"2023-04-24","cited_by_count":16,"area":null},{"id":"2305.19926","title":"Revisiting the Reliability of Psychological Scales on Large Language Models","created":"2023-05-31","cited_by_count":16,"area":null},{"id":"2310.06680","title":"Benchmarking and Explaining Large Language Model-based Code Generation: A Causality-Centric Approach","created":"2023-10-10","cited_by_count":15,"area":null},{"id":"2402.06598","title":"CigaR: Cost-efficient Program Repair with LLMs","created":"2024-02-09","cited_by_count":15,"area":null},{"id":"2407.05138","title":"Are LLMs Correctly Integrated into Software Systems?","created":"2024-07-06","cited_by_count":15,"area":"rag"},{"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":"2404.08877","title":"Aligning the Objective of LLM-based Program Repair","created":"2024-04-13","cited_by_count":12,"area":null},{"id":"2502.07803","title":"Reasoning-as-Logic-Units: Scaling Test-Time Reasoning in Large Language Models Through Logic Unit Alignment","created":"2025-02-05","cited_by_count":12,"area":"lr"},{"id":"2411.00932","title":"LLMs: A Game-Changer for Software Engineers?","created":"2024-11-01","cited_by_count":11,"area":null},{"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,"area":null},{"id":"2312.14856","title":"Turbulence: Systematically and Automatically Testing Instruction-Tuned Large Language Models for Code","created":"2023-12-22","cited_by_count":9,"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":"2510.03029","title":"Investigating The Smells of LLM Generated Code","created":"2025-10-03","cited_by_count":9,"area":null},{"id":"2306.03097","title":"Seeing Seeds Beyond Weeds: Green Teaming Generative AI for Beneficial Uses","created":"2023-05-30","cited_by_count":8,"area":"safety"},{"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":"2407.04065","title":"On the Workflows and Smells of Leaderboard Operations (LBOps): An Exploratory Study of Foundation Model Leaderboards","created":"2024-07-04","cited_by_count":6,"area":null},{"id":"2509.24380","title":"Agentic Services Computing","created":"2025-09-29","cited_by_count":6,"area":"agents"},{"id":"2309.12938","title":"Frustrated with Code Quality Issues? LLMs can Help!","created":"2023-09-22","cited_by_count":5,"area":null},{"id":"2310.09690","title":"Configuration Validation with Large Language Models","created":"2023-10-15","cited_by_count":4,"area":null},{"id":"2310.14211","title":"LUNA: A Model-Based Universal Analysis Framework for Large Language Models","created":"2023-10-22","cited_by_count":4,"area":null},{"id":"2503.05860","title":"Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Unified Approach for Elevating Benchmark Quality","created":"2025-03-07","cited_by_count":4,"area":null},{"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":"2504.15284","title":"EditLord: Learning Code Transformation Rules for Code Editing","created":"2025-03-10","cited_by_count":4,"area":null},{"id":"2506.17772","title":"PAGENT: Learning to Patch Software Engineering Agents","created":"2025-06-21","cited_by_count":4,"area":"agents"},{"id":"2507.11083","title":"Function-to-Style Guidance of LLMs for Code Translation","created":"2025-07-15","cited_by_count":4,"area":null},{"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":"2405.08848","title":"Automated Repair of AI Code with Large Language Models and Formal Verification","created":"2024-05-14","cited_by_count":3,"area":null},{"id":"2501.07892","title":"Leveraging Metamemory Agent for Enhanced Data-Free Code Generation in Large Language Models","created":"2025-01-14","cited_by_count":3,"area":"agents"},{"id":"2501.15081","title":"Can Large Language Models Be Trusted as Evolutionary Optimizers for Network-Structured Combinatorial Problems?","created":"2025-01-25","cited_by_count":3,"area":null},{"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":"2507.19909","title":"The Impact of Fine-tuning Large Language Models on Automated Program Repair","created":"2025-07-26","cited_by_count":3,"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":"2603.20334","title":"Procedural Refinement by LLM-driven Algorithmic Debugging for ARC-AGI-2","created":"2026-03-20","cited_by_count":2,"area":null},{"id":"2606.22110","title":"TraceView: Interactive Visualization of Agentic Program Repair Trajectories","created":"2026-06-20","cited_by_count":2,"area":"agents"},{"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":"2312.11701","title":"Opportunities and Challenges of Applying Large Language Models in Building Energy Efficiency and Decarbonization Studies: An Exploratory Overview","created":"2023-12-18","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":"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":"2501.00642","title":"Enabling New HDLs with Agents","created":"2024-12-31","cited_by_count":0,"area":"agents"},{"id":"2505.05744","title":"Harnessing LLMs Explanations to Boost Surrogate Models in Tabular Data Classification","created":"2025-05-09","cited_by_count":0,"area":null},{"id":"2509.19136","title":"On the Soundness and Consistency of LLM Agents for Executing Test Cases Written in Natural Language","created":"2025-09-23","cited_by_count":0,"area":"agents"},{"id":"2601.17604","title":"Human-Aligned Enhancement of Programming Answers with LLMs Guided by User Feedback","created":"2026-01-24","cited_by_count":0,"area":null},{"id":"2601.19923","title":"Structure-BiEval: A Self-Supervised, Dual-Track Framework for Decoupling Structure and Content in LLM Evaluation for Web Information Systems","created":"2026-01-09","cited_by_count":0,"area":null},{"id":"2604.15642","title":"HYPERHEURIST: A Simulated Annealing-Based Control Framework for LLM-Driven Code Generation in Optimized Hardware Design","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2605.08468","title":"PYTHALAB-MERA: Validation-Grounded Memory, Retrieval, and Acceptance Control for Frozen-LLM Coding Agents","created":"2026-05-08","cited_by_count":0,"area":"agents"},{"id":"2605.16046","title":"XSearch: Explainable Code Search via Concept-to-Code Alignment","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2605.17029","title":"Task Abstention for Large Language Models in Code Generation","created":"2026-05-16","cited_by_count":0,"area":null},{"id":"2605.17965","title":"BLAgent: Agentic RAG for File-Level Bug Localization","created":"2026-05-18","cited_by_count":0,"area":"rag"},{"id":"2609.00854","title":"Does Fault Localization Beat a Fresh Attempt? A Placebo-Controlled Study of Test-Guided Code Repair","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.07586","title":"A Tool-Augmented, GPT-4 Chatbot for Real-Time Repository Data Analysis","created":"2026-09-07","cited_by_count":0,"area":null}],"next_cursor":null}