{"list":"other","total":60,"rows":[{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"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":"2308.00352","title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","created":"2023-08-01","cited_by_count":1808},{"id":"2303.17760","title":"CAMEL: Communicative Agents for \"Mind\" Exploration of Large Language Model Society","created":"2023-03-31","cited_by_count":1395},{"id":"2308.03688","title":"AgentBench: Evaluating LLMs as Agents","created":"2023-08-07","cited_by_count":1267},{"id":"2105.09938","title":"Measuring Coding Challenge Competence With APPS","created":"2021-05-20","cited_by_count":902},{"id":"2402.01680","title":"Large Language Model based Multi-Agents: A Survey of Progress and Challenges","created":"2024-01-21","cited_by_count":769},{"id":"2308.10848","title":"AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors","created":"2023-08-21","cited_by_count":598},{"id":"2308.10620","title":"Large Language Models for Software Engineering: A Systematic Literature Review","created":"2023-08-21","cited_by_count":399},{"id":"2310.03302","title":"MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation","created":"2023-10-05","cited_by_count":366},{"id":"2306.03314","title":"Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents","created":"2023-06-05","cited_by_count":333},{"id":"2404.05427","title":"AutoCodeRover: Autonomous Program Improvement","created":"2024-04-08","cited_by_count":278},{"id":"2309.07544","title":"VerilogEval: Evaluating Large Language Models for Verilog Code Generation","created":"2023-09-14","cited_by_count":252},{"id":"2406.02818","title":"Chain of Agents: Large Language Models Collaborating on Long-Context Tasks","created":"2024-06-04","cited_by_count":206},{"id":"2503.16416","title":"Survey on Evaluation of LLM-based Agents","created":"2025-03-20","cited_by_count":204},{"id":"2310.11248","title":"CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion","created":"2023-10-17","cited_by_count":183},{"id":"2307.07221","title":"Software Testing with Large Language Models: Survey, Landscape, and Vision","created":"2023-07-14","cited_by_count":166},{"id":"1805.08949","title":"Learning to Mine Aligned Code and Natural Language Pairs from Stack Overflow","created":"2018-05-23","cited_by_count":165},{"id":"2210.14868","title":"Multi-lingual Evaluation of Code Generation Models","created":"2022-10-26","cited_by_count":159},{"id":"2507.21504","title":"Evaluation and Benchmarking of LLM Agents: A Survey","created":"2025-07-29","cited_by_count":152},{"id":"2401.03428","title":"Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospects","created":"2024-01-07","cited_by_count":132},{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116},{"id":"2212.10481","title":"Execution-Based Evaluation for Open-Domain Code Generation","created":"2022-12-20","cited_by_count":91},{"id":"2406.01304","title":"CodeR: Issue Resolving with Multi-Agent and Task Graphs","created":"2024-06-03","cited_by_count":91},{"id":"2406.14497","title":"CodeRAG-Bench: Can Retrieval Augment Code Generation?","created":"2024-06-20","cited_by_count":91},{"id":"2411.07781","title":"RedCode: Risky Code Execution and Generation Benchmark for Code Agents","created":"2024-11-12","cited_by_count":90},{"id":"2402.16694","title":"HumanEval-XL: A Multilingual Code Generation Benchmark for Cross-lingual Natural Language Generalization","created":"2024-02-26","cited_by_count":86},{"id":"2308.11396","title":"Towards an Understanding of Large Language Models in Software Engineering Tasks","created":"2023-08-22","cited_by_count":68},{"id":"2311.10372","title":"A Survey of Large Language Models for Code: Evolution, Benchmarking, and Future Trends","created":"2023-11-17","cited_by_count":66},{"id":"2303.09384","title":"LLMSecEval: A Dataset of Natural Language Prompts for Security Evaluations","created":"2023-03-16","cited_by_count":62},{"id":"2410.07331","title":"DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models","created":"2024-10-09","cited_by_count":58},{"id":"2312.17025","title":"Experiential Co-Learning of Software-Developing Agents","created":"2023-12-28","cited_by_count":57},{"id":"1910.02216","title":"JuICe: A Large Scale Distantly Supervised Dataset for Open Domain Context-based Code Generation","created":"2019-10-05","cited_by_count":49},{"id":"2506.05817","title":"CodeContests+: High-Quality Test Case Generation for Competitive Programming","created":"2025-06-06","cited_by_count":46},{"id":"2408.11053","title":"Revisiting VerilogEval: A Year of Improvements in Large-Language Models for Hardware Code Generation","created":"2024-08-20","cited_by_count":45},{"id":"1707.02553","title":"Guidelines for including grey literature and conducting multivocal literature reviews in software engineering","created":"2017-07-09","cited_by_count":41},{"id":"2405.01466","title":"A Systematic Literature Review on Large Language Models for Automated Program Repair","created":"2024-05-02","cited_by_count":37},{"id":"2310.19233","title":"Building Real-World Meeting Summarization Systems using Large Language Models: A Practical Perspective","created":"2023-10-30","cited_by_count":34},{"id":"2310.02003","title":"L2MAC: Large Language Model Automatic Computer for Extensive Code Generation","created":"2023-10-02","cited_by_count":30},{"id":"2310.08879","title":"A Critical Review of Large Language Model on Software Engineering: An Example from ChatGPT and Automated Program Repair","created":"2023-10-13","cited_by_count":29},{"id":"2503.01245","title":"Large Language Models for Code Generation: A Comprehensive Survey of Challenges, Techniques, Evaluation, and Applications","created":"2025-03-03","cited_by_count":26},{"id":"2505.16120","title":"LLM-Powered AI Agent Systems and Their Applications in Industry","created":"2025-05-22","cited_by_count":22},{"id":"2406.12655","title":"Benchmarks and Metrics for Evaluations of Code Generation: A Critical Review","created":"2024-06-18","cited_by_count":20},{"id":"2411.07464","title":"BudgetMLAgent: A Cost-Effective LLM Multi-Agent system for Automating Machine Learning Tasks","created":"2024-11-12","cited_by_count":19},{"id":"2412.05449","title":"Towards Effective GenAI Multi-Agent Collaboration: Design and Evaluation for Enterprise Applications","created":"2024-12-06","cited_by_count":19},{"id":"2404.04566","title":"Efficient and Green Large Language Models for Software Engineering: Literature Review, Vision, and the Road Ahead","created":"2024-04-06","cited_by_count":17},{"id":"2308.04929","title":"A/B Testing: A Systematic Literature Review","created":"2023-08-09","cited_by_count":16},{"id":"2412.05311","title":"DRC-Coder: Automated DRC Checker Code Generation Using LLM Autonomous Agent","created":"2024-11-28","cited_by_count":15},{"id":"2501.01277","title":"Language Models for Code Optimization: Survey, Challenges and Future Directions","created":"2025-01-02","cited_by_count":15},{"id":"2308.12415","title":"Benchmarking Causal Study to Interpret Large Language Models for Source Code","created":"2023-08-23","cited_by_count":14},{"id":"2106.06086","title":"PSB2: The Second Program Synthesis Benchmark Suite","created":"2021-06-10","cited_by_count":9},{"id":"2412.04093","title":"Practical Considerations for Agentic LLM Systems","created":"2024-12-05","cited_by_count":9},{"id":"2502.10884","title":"CodeA11y: Making AI Coding Assistants Useful for Accessible Web Development","created":"2025-02-15","cited_by_count":8},{"id":"2510.23642","title":"VisCoder2: Building Multi-Language Visualization Coding Agents","created":"2025-10-24","cited_by_count":6},{"id":"2511.07257","title":"Bridging the Prototype-Production Gap: A Multi-Agent System for Notebooks Transformation","created":"2025-11-10","cited_by_count":6},{"id":"2508.08882","title":"Reducing Cognitive Overhead in Tool Use via Multi-Small-Agent Reinforcement Learning","created":"2025-08-12","cited_by_count":3},{"id":"2407.06356","title":"Toward Programming Languages for Reasoning: Humans, Symbolic Systems, and AI Agents","created":"2024-07-08","cited_by_count":2},{"id":"2509.13144","title":"A Grey Literature Review of AI-Native Applications","created":"2025-09-16","cited_by_count":1}],"next_cursor":null}