{"total":59,"rows":[{"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":"2407.07959","title":"Source Code Summarization in the Era of Large Language Models","created":"2024-07-09","cited_by_count":31,"area":null},{"id":"2502.17601","title":"Representation Engineering for Large-Language Models: Survey and Research Challenges","created":"2025-02-24","cited_by_count":21,"area":"mechinterp"},{"id":"2604.03515","title":"Inside the Scaffold: A Source-Code Taxonomy of Coding Agent Architectures","created":"2026-04-03","cited_by_count":18,"area":"agents"},{"id":"2506.16136","title":"Seeing is Fixing: Cross-Modal Reasoning with Multimodal LLMs for Visual Software Issue Fixing","created":"2025-06-19","cited_by_count":12,"area":"lr"},{"id":"2506.20495","title":"ReCode: Updating Code API Knowledge with Reinforcement Learning","created":"2025-06-25","cited_by_count":12,"area":"alignment"},{"id":"2503.16508","title":"Conversational AI as a Coding Assistant: Understanding Programmers' Interactions with and Expectations from Large Language Models for Coding","created":"2025-03-14","cited_by_count":11,"area":null},{"id":"2602.23647","title":"SGAgent: Suggestion-Guided LLM-Based Multi-Agent Framework for Repository-Level Software Repair","created":"2026-02-27","cited_by_count":9,"area":"agents"},{"id":"2407.01646","title":"ESALE: Enhancing Code-Summary Alignment Learning for Source Code Summarization","created":"2024-07-01","cited_by_count":8,"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":"2510.00317","title":"MAVUL: Multi-Agent Vulnerability Detection via Contextual Reasoning and Interactive Refinement","created":"2025-09-30","cited_by_count":6,"area":null},{"id":"2407.08956","title":"Defending Code Language Models against Backdoor Attacks with Deceptive Cross-Entropy Loss","created":"2024-07-12","cited_by_count":5,"area":"safety"},{"id":"2408.01050","title":"The Impact of Hyperparameters on Large Language Model Inference Performance: An Evaluation of vLLM and HuggingFace Pipelines","created":"2024-08-02","cited_by_count":5,"area":null},{"id":"2503.22851","title":"RobuNFR: Evaluating the Robustness of Large Language Models on Non-Functional Requirements Aware Code Generation","created":"2025-03-28","cited_by_count":5,"area":null},{"id":"2505.04406","title":"YABLoCo: Yet Another Benchmark for Long Context Code Generation","created":"2025-05-07","cited_by_count":5,"area":null},{"id":"2505.15874","title":"Text-to-Pipeline: Bridging Natural Language and Data Preparation Pipelines","created":"2025-05-21","cited_by_count":5,"area":null},{"id":"2601.19494","title":"AACR-Bench: Evaluating Automatic Code Review with Holistic Repository-Level Context","created":"2026-01-27","cited_by_count":5,"area":null},{"id":"2605.25232","title":"Specification-Based Code-Text-Code Reengineering for LLM-Mediated Software Evolution","created":"2026-05-24","cited_by_count":5,"area":null},{"id":"2502.16071","title":"Improving Deep Assertion Generation via Fine-Tuning Retrieval-Augmented Pre-trained Language Models","created":"2025-02-22","cited_by_count":4,"area":"rag"},{"id":"2507.21285","title":"Curiosity by Design: An LLM-based Coding Assistant Asking Clarification Questions","created":"2025-07-28","cited_by_count":4,"area":null},{"id":"2511.01348","title":"The Future of Generative AI in Software Engineering: A Vision from Industry and Academia in the European GENIUS Project","created":"2025-11-03","cited_by_count":4,"area":null},{"id":"2511.07463","title":"Dynamic Stability of LLM-Generated Code","created":"2025-11-07","cited_by_count":4,"area":null},{"id":"2604.16790","title":"Bias in the Loop: Auditing LLM-as-a-Judge for Software Engineering","created":"2026-04-18","cited_by_count":4,"area":null},{"id":"2411.00005","title":"Mastering the Craft of Data Synthesis for CodeLLMs","created":"2024-10-16","cited_by_count":3,"area":"synth"},{"id":"2503.07556","title":"Novice Developers' Perspectives on Adopting LLMs for Software Development: A Systematic Literature Review","created":"2025-03-10","cited_by_count":3,"area":null},{"id":"2506.12958","title":"Domain Specific Benchmarks for Evaluating Multimodal Large Language Models","created":"2025-06-15","cited_by_count":3,"area":"mllm"},{"id":"2604.09409","title":"Do AI Coding Agents Log Like Humans? An Empirical Study","created":"2026-04-10","cited_by_count":3,"area":"agents"},{"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":"2502.10696","title":"Improving Retrieval-Augmented Deep Assertion Generation via Joint Training","created":"2025-02-15","cited_by_count":2,"area":"rag"},{"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":"2601.10773","title":"LogicLens: Leveraging Semantic Code Graph to explore Multi Repository large systems","created":"2026-01-15","cited_by_count":2,"area":null},{"id":"2608.03392","title":"Self-Evolving Coding Agents","created":"2026-08-04","cited_by_count":2,"area":"agents"},{"id":"2505.04084","title":"An Empirical Study of OpenAI API Discussions on Stack Overflow","created":"2025-05-07","cited_by_count":1,"area":null},{"id":"2508.15411","title":"Foundational Design Principles and Patterns for Building Robust and Adaptive GenAI-Native Systems","created":"2025-08-21","cited_by_count":1,"area":null},{"id":"2512.21681","title":"Exploring the Security Threats of Retriever Backdoors in Retrieval-Augmented Code Generation","created":"2025-12-25","cited_by_count":1,"area":"rag"},{"id":"2603.22018","title":"Do Papers Tell the Whole Story? A Benchmark and Framework for Uncovering Hidden Implementation Gaps in Bioinformatics","created":"2026-03-23","cited_by_count":1,"area":null},{"id":"2604.12379","title":"Beyond Output Correctness: Benchmarking and Evaluating Large Language Model Reasoning in Coding Tasks","created":"2026-04-14","cited_by_count":1,"area":"lr"},{"id":"2605.05267","title":"Bridging Generation and Training: A Systematic Review of Quality Issues in LLMs for Code","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2605.06279","title":"Correct Code, Vulnerable Dependencies: A Large Scale Measurement Study of LLM-Specified Library Versions","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2607.01211","title":"Are Performance-Optimization Benchmarks Reliably Measuring Coding Agents?","created":"2026-07-01","cited_by_count":1,"area":"agents"},{"id":"2607.18886","title":"TraceDev: A Traceability-Driven Multi-agent Framework for Requirement-to-Code Development","created":"2026-07-21","cited_by_count":1,"area":"agents"},{"id":"2505.10640","title":"The Hitchhikers Guide to Production-ready Trustworthy Foundation Model powered Software (FMware)","created":"2025-05-15","cited_by_count":0,"area":null},{"id":"2505.19625","title":"Search-Based Software Engineering and AI Foundation Models: Current Landscape and Future Roadmap","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2507.12665","title":"Single Conversation Methodology: A Human-Centered Protocol for AI-Assisted Software Development","created":"2025-07-16","cited_by_count":0,"area":null},{"id":"2508.17353","title":"Detecting Struggling Student Programmers using Proficiency Taxonomies","created":"2025-08-24","cited_by_count":0,"area":null},{"id":"2511.07458","title":"REFLEX: Reference-Free Evaluation of Log Summarization via Large Language Model Judgment","created":"2025-11-06","cited_by_count":0,"area":null},{"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":"2604.23816","title":"Query2Diagram: Answering Developer Queries with UML Diagrams","created":"2026-04-26","cited_by_count":0,"area":null},{"id":"2605.23091","title":"Security of LLM-generated Code: A Comparative Analysis","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2605.25536","title":"A Tertiary Review of Large Language Model-Based Code Generating Tasks: Trends, Challenges, and Future Directions","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.15283","title":"AI-driven Software Development: A Pragmatic Path to Agentic Development Processes","created":"2026-06-13","cited_by_count":0,"area":"agents"},{"id":"2607.04579","title":"LLM-Driven CI-CD Workflow Intelligence for Cyber Systems Engineering","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.07881","title":"Functional and Secure Code Generation with Task Vectors","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2607.09101","title":"Multi-Agent LLM Collaboration for Unit Test Generation via Human-Testing-Inspired Workflows","created":"2026-07-10","cited_by_count":0,"area":"agents"},{"id":"2607.16564","title":"ReqGenX: An Empirical Study of Atomic Decomposition, Artifact Regeneration, and Reconstruction for Legacy SRS Documents","created":"2026-07-18","cited_by_count":0,"area":null},{"id":"2607.28307","title":"From Textual Requirements to Microservice Architectures - A Comprehensive Evaluation of LLM-Based Design Synthesis","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2609.37405","title":"Complexity-Aware Evaluation of LLM Comprehension","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.01428","title":"Generalization Is Stability, Not Accuracy: Multi-Axis Evaluation of LLMs","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}