{"total":39,"rows":[{"id":"2310.02170","title":"A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration","created":"2023-10-03","cited_by_count":290,"area":"agents"},{"id":"2402.17553","title":"OmniACT: A Dataset and Benchmark for Enabling Multimodal Generalist Autonomous Agents for Desktop and Web","created":"2024-02-27","cited_by_count":157,"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":"2411.00622","title":"Lingma SWE-GPT: An Open Development-Process-Centric Language Model for Automated Software Improvement","created":"2024-11-01","cited_by_count":61,"area":"agents"},{"id":"2504.00255","title":"SciReplicate-Bench: Benchmarking LLMs in Agent-driven Algorithmic Reproduction from Research Papers","created":"2025-03-31","cited_by_count":43,"area":"agents"},{"id":"2501.07811","title":"CodeCoR: An LLM-Based Self-Reflective Multi-Agent Framework for Code Generation","created":"2025-01-14","cited_by_count":34,"area":"agents"},{"id":"2411.05451","title":"WorkflowLLM: Enhancing Workflow Orchestration Capability of Large Language Models","created":"2024-11-08","cited_by_count":30,"area":"agents"},{"id":"2503.07010","title":"ProjectEval: A Benchmark for Programming Agents Automated Evaluation on Project-Level Code Generation","created":"2025-03-10","cited_by_count":26,"area":"agents"},{"id":"2507.16459","title":"Towards Enforcing Company Policy Adherence in Agentic Workflows","created":"2025-07-22","cited_by_count":18,"area":"agents"},{"id":"2511.18538","title":"From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence","created":"2025-11-23","cited_by_count":15,"area":"agents"},{"id":"2503.14340","title":"MANTRA: Enhancing Automated Method-Level Refactoring with Contextual RAG and Multi-Agent LLM Collaboration","created":"2025-03-18","cited_by_count":10,"area":"agents"},{"id":"2604.23580","title":"PhysCodeBench: Benchmarking Physics-Aware Symbolic Simulation of 3D Scenes via Self-Corrective Multi-Agent Refinement","created":"2026-04-26","cited_by_count":10,"area":"agents"},{"id":"2503.14713","title":"TestForge: Feedback-Driven, Agentic Test Suite Generation","created":"2025-03-18","cited_by_count":9,"area":"agents"},{"id":"2507.23096","title":"ChatVis: Large Language Model Agent for Generating Scientific Visualizations","created":"2025-07-30","cited_by_count":7,"area":"agents"},{"id":"2504.13472","title":"CodeVisionary: An Agent-based Framework for Evaluating Large Language Models in Code Generation","created":"2025-04-18","cited_by_count":6,"area":"agents"},{"id":"2508.01012","title":"AutoEDA: Enabling EDA Flow Automation through Microservice-Based LLM Agents","created":"2025-08-01","cited_by_count":6,"area":"agents"},{"id":"2511.03404","title":"Towards Realistic Project-Level Code Generation via Multi-Agent Collaboration and Semantic Architecture Modeling","created":"2025-11-05","cited_by_count":6,"area":"agents"},{"id":"2510.26852","title":"CATArena: Evaluating Evolutionary Capabilities of Code Agents via Iterative Tournaments","created":"2025-10-30","cited_by_count":5,"area":"agents"},{"id":"2603.24631","title":"Coherence Collapse: Diagnosing Why Code Agents Fail After Reaching the Right Code","created":"2026-03-25","cited_by_count":5,"area":"agents"},{"id":"2506.00739","title":"DefenderBench: A Toolkit for Evaluating Language Agents in Cybersecurity Environments","created":"2025-05-31","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":"2502.15153","title":"When Disagreements Elicit Robustness: Investigating Self-Repair Capabilities under LLM Multi-Agent Disagreements","created":"2025-02-21","cited_by_count":3,"area":"agents"},{"id":"2503.07693","title":"Fully Autonomous Programming using Iterative Multi-Agent Debugging with Large Language Models","created":"2025-03-10","cited_by_count":3,"area":"agents"},{"id":"2608.11386","title":"The Devil Is in the Interface: Evaluating How Tool Architecture Shapes Coding Agent Behavior","created":"2026-08-11","cited_by_count":3,"area":"agents"},{"id":"2601.02200","title":"Code for Machines, Not Just Humans: Quantifying AI-Friendliness with Code Health Metrics","created":"2026-01-05","cited_by_count":2,"area":"agents"},{"id":"2605.30105","title":"EvoRepair: Enhancing Vulnerability Repair Agents Through Experience-Based Self-Evolution","created":"2026-05-28","cited_by_count":2,"area":"agents"},{"id":"2506.06175","title":"Does It Run and Is That Enough? Revisiting Text-to-Chart Generation with a Multi-Agent Approach","created":"2025-06-06","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":"2606.22647","title":"RAVEN: Agentic RAG for Automated Vulnerability Repair","created":"2026-06-21","cited_by_count":1,"area":"agents"},{"id":"2508.20866","title":"AVIATOR: Towards AI-Agentic Vulnerability Injection Workflow for High-Fidelity, Large-Scale Code Security Dataset","created":"2025-08-28","cited_by_count":0,"area":"agents"},{"id":"2511.20656","title":"Context-Aware Visual Prompting: Automating Geospatial Web Dashboards with Large Language Models and Agent Self-Validation for Decision Support","created":"2025-10-10","cited_by_count":0,"area":"agents"},{"id":"2602.05353","title":"AgentXRay: White-Boxing Agentic Systems via Workflow Reconstruction","created":"2026-02-05","cited_by_count":0,"area":"agents"},{"id":"2603.02510","title":"ParEVO: Synthesizing Code for Irregular Data: High-Performance Parallelism through Agentic Evolution","created":"2026-03-03","cited_by_count":0,"area":"agents"},{"id":"2603.26845","title":"GISclaw: A Comprehensive Open-Source LLM Agent System for Realistic Multi-Step Geospatial Analysis","created":"2026-03-27","cited_by_count":0,"area":"agents"},{"id":"2604.06762","title":"ARuleCon: Agentic Security Rule Conversion","created":"2026-04-08","cited_by_count":0,"area":"agents"},{"id":"2605.17444","title":"MemRepair: Hierarchical Memory for Agentic Repository-Level Vulnerability Repair","created":"2026-05-17","cited_by_count":0,"area":"agents"},{"id":"2609.04898","title":"RefactorPlatform: An Open-Source Harness for Controlled Evaluation of Repository-Scale Refactoring Agents","created":"2026-09-04","cited_by_count":0,"area":"agents"},{"id":"2609.14413","title":"A Hybrid Dependency-Aware Framework for Task Decomposition and Dynamic Agent Generation in Oracle-to-PostgreSQL Migration","created":"2026-09-13","cited_by_count":0,"area":"agents"},{"id":"2609.32424","title":"CyberClear: A Benchmark for LLM Agent Systems on APT Attack Chain Provenance","created":"2026-09-26","cited_by_count":0,"area":"agents"}],"next_cursor":null}