{"total":75,"rows":[{"id":"2308.03688","title":"AgentBench: Evaluating LLMs as Agents","created":"2023-08-07","cited_by_count":1267,"area":"agents"},{"id":"2307.07924","title":"ChatDev: Communicative Agents for Software Development","created":"2023-07-16","cited_by_count":919,"area":"agents"},{"id":"2501.04227","title":"Agent Laboratory: Using LLM Agents as Research Assistants","created":"2025-01-08","cited_by_count":425,"area":"agents"},{"id":"2309.10691","title":"MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback","created":"2023-09-19","cited_by_count":297,"area":"agents"},{"id":"2401.07339","title":"CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges","created":"2024-01-14","cited_by_count":282,"area":"agents"},{"id":"2408.02479","title":"From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Future","created":"2024-08-05","cited_by_count":86,"area":"agents"},{"id":"2504.08703","title":"SWE-PolyBench: A multi-language benchmark for repository level evaluation of coding agents","created":"2025-04-11","cited_by_count":85,"area":"agents"},{"id":"2407.12821","title":"AutoFlow: Automated Workflow Generation for Large Language Model Agents","created":"2024-07-01","cited_by_count":83,"area":"agents"},{"id":"2401.00812","title":"If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agents","created":"2024-01-01","cited_by_count":79,"area":"agents"},{"id":"2409.00899","title":"MarsCode Agent: AI-native Automated Bug Fixing","created":"2024-09-02","cited_by_count":71,"area":"agents"},{"id":"2409.16299","title":"HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale","created":"2024-09-09","cited_by_count":61,"area":"agents"},{"id":"2503.22458","title":"Evaluating LLM-based Agents for Multi-Turn Conversations: A Survey","created":"2025-03-28","cited_by_count":57,"area":"agents"},{"id":"2605.18747","title":"Code as Agent Harness","created":"2026-05-18","cited_by_count":47,"area":"agents"},{"id":"2407.16667","title":"RedAgent: Red Teaming Large Language Models with Context-aware Autonomous Language Agent","created":"2024-07-23","cited_by_count":44,"area":"agents"},{"id":"2407.01231","title":"MIRAI: Evaluating LLM Agents for Event Forecasting","created":"2024-07-01","cited_by_count":41,"area":"agents"},{"id":"2312.13010","title":"AgentCoder: Multi-Agent-based Code Generation with Iterative Testing and Optimisation","created":"2023-12-20","cited_by_count":35,"area":"agents"},{"id":"2409.10737","title":"AutoSafeCoder: A Multi-Agent Framework for Securing LLM Code Generation through Static Analysis and Fuzz Testing","created":"2024-09-16","cited_by_count":35,"area":"agents"},{"id":"2502.05664","title":"CODESIM: Multi-Agent Code Generation and Problem Solving through Simulation-Driven Planning and Debugging","created":"2025-02-08","cited_by_count":32,"area":"agents"},{"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":"2406.00215","title":"HumanEvalComm: Benchmarking the Communication Competence of Code Generation for LLMs and LLM Agent","created":"2024-05-31","cited_by_count":24,"area":"agents"},{"id":"2503.06047","title":"DSGBench: A Diverse Strategic Game Benchmark for Evaluating LLM-based Agents in Complex Decision-Making Environments","created":"2025-03-08","cited_by_count":23,"area":"agents"},{"id":"2402.01411","title":"CodePori: Large-Scale System for Autonomous Software Development Using Multi-Agent Technology","created":"2024-02-02","cited_by_count":22,"area":"agents"},{"id":"2603.24477","title":"Composer 2 Technical Report","created":"2026-03-25","cited_by_count":22,"area":"agents"},{"id":"2506.02454","title":"Multimodal DeepResearcher: Generating Text-Chart Interleaved Reports From Scratch with Agentic Framework","created":"2025-06-03","cited_by_count":21,"area":"agents"},{"id":"2503.21557","title":"debug-gym: A Text-Based Environment for Interactive Debugging","created":"2025-03-27","cited_by_count":19,"area":"agents"},{"id":"2503.03196","title":"SpiritSight Agent: Advanced GUI Agent with One Look","created":"2025-03-05","cited_by_count":18,"area":"agents"},{"id":"2510.24702","title":"Agent Data Protocol: Unifying Datasets for Diverse, Effective Fine-tuning of LLM Agents","created":"2025-10-28","cited_by_count":17,"area":"agents"},{"id":"2501.12432","title":"Divide-Then-Aggregate: An Efficient Tool Learning Method via Parallel Tool Invocation","created":"2025-01-21","cited_by_count":16,"area":"agents"},{"id":"2507.00014","title":"SWE-Bench-CL: Continual Learning for Coding Agents","created":"2025-06-13","cited_by_count":14,"area":"agents"},{"id":"2410.01242","title":"RGD: Multi-LLM Based Agent Debugger via Refinement and Generation Guidance","created":"2024-10-02","cited_by_count":12,"area":"agents"},{"id":"2606.20683","title":"From Question Answering to Task Completion: A Survey on Agent System and Harness Design","created":"2026-06-14","cited_by_count":12,"area":"agents"},{"id":"2511.05459","title":"SWE-Compass: Towards Unified Evaluation of Agentic Coding Abilities for Large Language Models","created":"2025-11-07","cited_by_count":11,"area":"agents"},{"id":"2405.17009","title":"Position: Foundation Agents as the Paradigm Shift for Decision Making","created":"2024-05-27","cited_by_count":9,"area":"agents"},{"id":"2503.14713","title":"TestForge: Feedback-Driven, Agentic Test Suite Generation","created":"2025-03-18","cited_by_count":9,"area":"agents"},{"id":"2504.03424","title":"The AI Cosmologist I: An Agentic System for Automated Data Analysis","created":"2025-04-04","cited_by_count":9,"area":"agents"},{"id":"2405.06907","title":"AIOS Compiler: LLM as Interpreter for Natural Language Programming and Flow Programming of AI Agents","created":"2024-05-11","cited_by_count":8,"area":"agents"},{"id":"2408.01916","title":"MAO: A Framework for Process Model Generation with Multi-Agent Orchestration","created":"2024-08-04","cited_by_count":8,"area":"agents"},{"id":"2504.04220","title":"AdaCoder: An Adaptive Planning and Multi-Agent Framework for Function-Level Code Generation","created":"2025-04-05","cited_by_count":8,"area":"agents"},{"id":"2408.13406","title":"Collaboration Dynamics and Reliability Challenges of Multi-Agent LLM Systems in Finite Element Analysis","created":"2024-08-23","cited_by_count":6,"area":"agents"},{"id":"2410.22339","title":"DAWN: Designing Distributed Agents in a Worldwide Network","created":"2024-10-11","cited_by_count":6,"area":"agents"},{"id":"2502.06589","title":"Hephaestus: Improving Fundamental Agent Capabilities of Large Language Models through Continual Pre-Training","created":"2025-02-10","cited_by_count":6,"area":"agents"},{"id":"2407.10499","title":"CIBench: Evaluating Your LLMs with a Code Interpreter Plugin","created":"2024-07-15","cited_by_count":5,"area":"agents"},{"id":"2409.00985","title":"Co-Learning: Code Learning for Multi-Agent Reinforcement Collaborative Framework with Conversational Natural Language Interfaces","created":"2024-09-02","cited_by_count":5,"area":"agents"},{"id":"2503.06791","title":"AutoMisty: A Multi-Agent LLM Framework for Automated Code Generation in the Misty Social Robot","created":"2025-03-09","cited_by_count":5,"area":"agents"},{"id":"2602.01966","title":"Self-Consolidation for Self-Evolving Agents","created":"2026-02-02","cited_by_count":5,"area":"agents"},{"id":"2405.16887","title":"A Large Language Model-based multi-agent manufacturing system for intelligent shopfloor","created":"2024-05-27","cited_by_count":4,"area":"agents"},{"id":"2503.12217","title":"TFHE-Coder: Evaluating LLM-agentic Fully Homomorphic Encryption Code Generation","created":"2025-03-15","cited_by_count":4,"area":"agents"},{"id":"2606.22082","title":"CodeTeam: An LLM-Powered Multi-Agent Framework for Repository-Level Code Generation","created":"2026-06-20","cited_by_count":4,"area":"agents"},{"id":"2410.09117","title":"REDO: Execution-Free Runtime Error Detection for COding Agents","created":"2024-10-10","cited_by_count":2,"area":"agents"},{"id":"2508.15940","title":"ASIC-Agent: An Autonomous Multi-Agent System for ASIC Design with Benchmark Evaluation","created":"2025-08-21","cited_by_count":2,"area":"agents"},{"id":"2510.08665","title":"RA-Gen: A Controllable Code Generation Framework Using ReAct for Multi-Agent Task Execution","created":"2025-10-09","cited_by_count":2,"area":"agents"},{"id":"2510.08804","title":"MOSAIC: Multi-agent Orchestration for Task-Intelligent Scientific Coding","created":"2025-10-09","cited_by_count":2,"area":"agents"},{"id":"2607.02186","title":"UA-ChatDev: Uncertainty-Aware Multi-Agent Collaboration for Reliable Software Development","created":"2026-07-02","cited_by_count":2,"area":"agents"},{"id":"2607.12463","title":"Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models","created":"2026-07-14","cited_by_count":2,"area":"agents"},{"id":"2409.06568","title":"Think-on-Process: Dynamic Process Generation for Collaborative Development of Multi-Agent System","created":"2024-09-10","cited_by_count":1,"area":"agents"},{"id":"2507.18812","title":"MemoCoder: Automated Function Synthesis using LLM-Supported Agents","created":"2025-07-24","cited_by_count":1,"area":"agents"},{"id":"2601.23009","title":"SolAgent: A Specialized Multi-Agent Framework for Solidity Code Generation","created":"2026-01-30","cited_by_count":1,"area":"agents"},{"id":"2603.03233","title":"AI-for-Science Low-code Platform with Bayesian Adversarial Multi-Agent Framework","created":"2026-03-03","cited_by_count":1,"area":"agents"},{"id":"2603.09004","title":"Can AI Agents Generate Microservices? How Far are We?","created":"2026-03-09","cited_by_count":1,"area":"agents"},{"id":"2604.10235","title":"CodeComp: Structural KV Cache Compression for Agentic Coding","created":"2026-04-11","cited_by_count":1,"area":"agents"},{"id":"2605.15334","title":"From I/O to Code with Discovery Agent","created":"2026-05-14","cited_by_count":1,"area":"agents"},{"id":"2606.10933","title":"Frontier Coding Agents Use Metaprogramming to Adapt to Unfamiliar Programming Languages","created":"2026-06-09","cited_by_count":1,"area":"agents"},{"id":"2607.01211","title":"Are Performance-Optimization Benchmarks Reliably Measuring Coding Agents?","created":"2026-07-01","cited_by_count":1,"area":"agents"},{"id":"2407.10049","title":"AutoGRAMS: Autonomous Graphical Agent Modeling Software","created":"2024-07-14","cited_by_count":0,"area":"agents"},{"id":"2412.08069","title":"DialogAgent: An Auto-engagement Agent for Code Question Answering Data Production","created":"2024-12-11","cited_by_count":0,"area":"agents"},{"id":"2508.11665","title":"StackPilot: Autonomous Function Agents for Scalable and Environment-Free Code Execution","created":"2025-08-06","cited_by_count":0,"area":"agents"},{"id":"2510.02669","title":"AutoMaAS: Self-Evolving Multi-Agent Architecture Search for Large Language Models","created":"2025-10-03","cited_by_count":0,"area":"agents"},{"id":"2511.03934","title":"PEFA-AI: Advancing Open-source LLMs for RTL generation using Progressive Error Feedback Agentic-AI","created":"2025-11-06","cited_by_count":0,"area":"agents"},{"id":"2604.23106","title":"No Test Cases, No Problem: Distillation-Driven Code Generation for Scientific Workflows","created":"2026-04-25","cited_by_count":0,"area":"agents"},{"id":"2606.13097","title":"Functional Cache Grafting: Robust and Rapid Code-Policy Synthesis for Embodied Agents","created":"2026-06-11","cited_by_count":0,"area":"agents"},{"id":"2607.00035","title":"Making Failure Safe: A Constrained, Verifiable Agent Framework for Open-Web Data Collection","created":"2026-06-25","cited_by_count":0,"area":"agents"},{"id":"2607.05659","title":"Agents with Feelings? Personality and Emotion in Multi-Agent Software Teams","created":"2026-07-06","cited_by_count":0,"area":"agents"},{"id":"2607.20499","title":"ExecuGraph: A Multi-Agent, Execution-Grounded Framework for Reliable Backend Code Synthesis with Large Language Models","created":"2026-06-18","cited_by_count":0,"area":"agents"},{"id":"2607.27167","title":"SpecFirst: Behavioral Specification Elicitation as a First-Class Step in Agent-Based Program Synthesis from Scratch","created":"2026-07-29","cited_by_count":0,"area":"agents"},{"id":"2608.05822","title":"Agent-Based Test Assertion Generation via Diverse Perspective Aggregation","created":"2026-08-06","cited_by_count":0,"area":"agents"}],"next_cursor":null}