{"total":83,"rows":[{"id":"2410.10934","title":"Agent-as-a-Judge: Evaluate Agents with Agents","created":"2024-10-14","cited_by_count":238,"area":"agents"},{"id":"2409.02977","title":"Large Language Model-Based Agents for Software Engineering: A Survey","created":"2024-09-04","cited_by_count":178,"area":"agents"},{"id":"2404.04834","title":"LLM-Based Multi-Agent Systems for Software Engineering: Literature Review, Vision and the Road Ahead","created":"2024-04-07","cited_by_count":155,"area":"agents"},{"id":"2507.21504","title":"Evaluation and Benchmarking of LLM Agents: A Survey","created":"2025-07-29","cited_by_count":152,"area":"agents"},{"id":"2406.12952","title":"SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents","created":"2024-06-18","cited_by_count":133,"area":"agents"},{"id":"2406.01637","title":"Teams of LLM Agents can Exploit Zero-Day Vulnerabilities","created":"2024-06-02","cited_by_count":95,"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":"2504.16129","title":"MARFT: Multi-Agent Reinforcement Fine-Tuning","created":"2025-04-21","cited_by_count":52,"area":"agents"},{"id":"2412.10133","title":"You Name It, I Run It: An LLM Agent to Execute Tests of Arbitrary Projects","created":"2024-12-13","cited_by_count":47,"area":"agents"},{"id":"2511.18423","title":"General Agentic Memory Via Deep Research","created":"2025-11-23","cited_by_count":47,"area":"agents"},{"id":"2411.12924","title":"Human-In-the-Loop Software Development Agents","created":"2024-11-19","cited_by_count":42,"area":"agents"},{"id":"2502.20073","title":"Collab-Overcooked: Benchmarking and Evaluating Large Language Models as Collaborative Agents","created":"2025-02-27","cited_by_count":41,"area":"agents"},{"id":"2512.02393","title":"Process-Centric Analysis of Agentic Software Systems","created":"2025-12-02","cited_by_count":24,"area":"agents"},{"id":"2411.10213","title":"An Empirical Study on LLM-based Agents for Automated Bug Fixing","created":"2024-11-15","cited_by_count":23,"area":"agents"},{"id":"2508.02744","title":"Large Language Model-based Data Science Agent: A Survey","created":"2025-08-02","cited_by_count":23,"area":"agents"},{"id":"2510.05174","title":"Emergent Coordination in Multi-Agent Language Models","created":"2025-10-05","cited_by_count":23,"area":"agents"},{"id":"2601.13295","title":"CooperBench: Why Coding Agents Cannot be Your Teammates Yet","created":"2026-01-19","cited_by_count":23,"area":"agents"},{"id":"2502.02747","title":"PatchPilot: A Cost-Efficient Software Engineering Agent with Early Attempts on Formal Verification","created":"2025-02-04","cited_by_count":22,"area":"agents"},{"id":"2412.06294","title":"Beyond pip install: Evaluating LLM Agents for the Automated Installation of Python Projects","created":"2024-12-09","cited_by_count":21,"area":"agents"},{"id":"2603.12644","title":"Uncovering Security Threats and Architecting Defenses in Autonomous Agents: A Case Study of OpenClaw","created":"2026-03-13","cited_by_count":20,"area":"agents"},{"id":"2603.05344","title":"Building Effective AI Coding Agents for the Terminal: Scaffolding, Harness, Context Engineering, and Lessons Learned","created":"2026-03-05","cited_by_count":18,"area":"agents"},{"id":"2509.09853","title":"SWE-Effi: Re-Evaluating Software AI Agent System Effectiveness Under Resource Constraints","created":"2025-09-11","cited_by_count":17,"area":"agents"},{"id":"2510.09721","title":"A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic System","created":"2025-10-10","cited_by_count":15,"area":"agents"},{"id":"2512.01939","title":"An Empirical Study of Agent Developer Practices in AI Agent Frameworks","created":"2025-12-01","cited_by_count":14,"area":"agents"},{"id":"2602.03695","title":"Agent Primitives: Reusable Latent Building Blocks for Multi-Agent Systems","created":"2026-02-03","cited_by_count":14,"area":"agents"},{"id":"2511.02755","title":"Controlling Performance and Budget of a Centralized Multi-agent LLM System with Reinforcement Learning","created":"2025-11-04","cited_by_count":13,"area":"agents"},{"id":"2607.09510","title":"Failure as a Process: An Anatomy of CLI Coding Agent Trajectories","created":"2026-07-10","cited_by_count":13,"area":"agents"},{"id":"2412.10422","title":"AutoPrep: Natural Language Question-Aware Data Preparation with a Multi-Agent Framework","created":"2024-12-10","cited_by_count":12,"area":"agents"},{"id":"2509.16736","title":"Towards Transparent and Incentive-Compatible Collaboration in Decentralized LLM Multi-Agent Systems: A Blockchain-Driven Approach","created":"2025-09-20","cited_by_count":12,"area":"agents"},{"id":"2507.10621","title":"Game Theory Meets LLM and Agentic AI: Reimagining Cybersecurity for the Age of Intelligent Threats","created":"2025-07-14","cited_by_count":11,"area":"agents"},{"id":"2507.11988","title":"Aime: Towards Fully-Autonomous Multi-Agent Framework","created":"2025-07-16","cited_by_count":9,"area":"agents"},{"id":"2602.06593","title":"AgentStepper: Interactive Debugging of Software Development Agents","created":"2026-02-06","cited_by_count":9,"area":"agents"},{"id":"2506.12482","title":"Tiered Agentic Oversight: A Hierarchical Multi-Agent System for Healthcare Safety","created":"2025-06-14","cited_by_count":8,"area":"agents"},{"id":"2602.11541","title":"Budget-Constrained Agentic Large Language Models: Intention-Based Planning for Costly Tool Use","created":"2026-02-12","cited_by_count":8,"area":"agents"},{"id":"2505.16086","title":"Optimizing LLM-Based Multi-Agent System with Textual Feedback: A Case Study on Software Development","created":"2025-05-22","cited_by_count":7,"area":"agents"},{"id":"2605.06623","title":"MASPO: Joint Prompt Optimization for LLM-based Multi-Agent Systems","created":"2026-05-07","cited_by_count":7,"area":"agents"},{"id":"2406.07275","title":"DCA-Bench: A Benchmark for Dataset Curation Agents","created":"2024-06-11","cited_by_count":6,"area":"agents"},{"id":"2509.14483","title":"An LLM-based multi-agent framework for agile effort estimation","created":"2025-09-17","cited_by_count":6,"area":"agents"},{"id":"2510.23761","title":"TDFlow: Agentic Workflows for Test Driven Development","created":"2025-10-27","cited_by_count":6,"area":"agents"},{"id":"2512.22256","title":"Agentic Software Issue Resolution with Large Language Models: A Survey","created":"2025-12-24","cited_by_count":6,"area":"agents"},{"id":"2605.20563","title":"Multi-agent Collaboration with State Management","created":"2026-05-19","cited_by_count":6,"area":"agents"},{"id":"2609.00006","title":"Harness Engineering: Anatomy, Architecture, and Evolution of Coding Agents -- A Source-Code Study of Eleven Systems","created":"2026-07-15","cited_by_count":6,"area":"agents"},{"id":"2509.25894","title":"Red Teaming Program Repair Agents: When Correct Patches can Hide Vulnerabilities","created":"2025-09-30","cited_by_count":5,"area":"agents"},{"id":"2510.03902","title":"Multi-Agent Code-Orchestrated Generation for Reliable Infrastructure-as-Code","created":"2025-10-04","cited_by_count":5,"area":"agents"},{"id":"2602.03128","title":"Architectural Design, Not Only Model Intelligence, Governs Multi-Agent LLM Performance","created":"2026-02-03","cited_by_count":5,"area":"agents"},{"id":"2604.13120","title":"AgentForge: Execution-Grounded Multi-Agent LLM Framework for Autonomous Software Engineering","created":"2026-04-13","cited_by_count":5,"area":"agents"},{"id":"2607.00990","title":"SWE-Doctor: Guiding Software Engineering Agents with Runtime Diagnosis from Multi-Faceted Bug Reproduction Tests","created":"2026-07-01","cited_by_count":5,"area":"agents"},{"id":"2608.13317","title":"StateBridge: Training-free Hidden-state Alignment for Latent Communication in LLM Multi-Agent Systems","created":"2026-08-13","cited_by_count":5,"area":"agents"},{"id":"2412.13437","title":"Deploying Foundation Model Powered Agent Services: A Survey","created":"2024-12-18","cited_by_count":4,"area":"agents"},{"id":"2506.13324","title":"Towards Pervasive Distributed Agentic Generative AI -- A State of The Art","created":"2025-06-16","cited_by_count":4,"area":"agents"},{"id":"2510.12120","title":"Towards Engineering Multi-Agent LLMs: A Protocol-Driven Approach","created":"2025-10-14","cited_by_count":4,"area":"agents"},{"id":"2410.06949","title":"Towards Exception Safety Code Generation with Intermediate Representation Agents Framework","created":"2024-10-09","cited_by_count":3,"area":"agents"},{"id":"2511.08475","title":"Designing LLM-based Multi-Agent Systems for Software Engineering Tasks: Quality Attributes, Design Patterns and Rationale","created":"2025-11-11","cited_by_count":3,"area":"agents"},{"id":"2605.06717","title":"Agentic Coding Needs Proactivity, Not Just Autonomy","created":"2026-05-07","cited_by_count":3,"area":"agents"},{"id":"2608.13867","title":"Engineering Reliable Coding Agents: Evaluating and Operating the System Around the Model","created":"2026-08-14","cited_by_count":3,"area":"agents"},{"id":"2412.11713","title":"Seeker: Towards Exception Safety Code Generation with Intermediate Language Agents Framework","created":"2024-12-16","cited_by_count":2,"area":"agents"},{"id":"2511.11012","title":"Beyond Accuracy: Behavioral Dynamics of Agentic Multi-Hunk Repair","created":"2025-11-14","cited_by_count":2,"area":"agents"},{"id":"2511.20663","title":"MTTR-A: Measuring Cognitive Recovery Latency in Multi-Agent Systems","created":"2025-11-08","cited_by_count":2,"area":"agents"},{"id":"2601.13933","title":"VulnResolver: A Hybrid Agent Framework for LLM-Based Automated Vulnerability Issue Resolution","created":"2026-01-20","cited_by_count":2,"area":"agents"},{"id":"2509.16713","title":"OPEN-THEATRE: An Open-Source Toolkit for LLM-based Interactive Drama","created":"2025-09-20","cited_by_count":1,"area":"agents"},{"id":"2509.26126","title":"The Hunger Game Debate: On the Emergence of Over-Competition in Multi-Agent Systems","created":"2025-09-30","cited_by_count":1,"area":"agents"},{"id":"2510.14512","title":"Helmsman: Autonomous Synthesis of Federated Learning Systems via Collaborative LLM Agents","created":"2025-10-16","cited_by_count":1,"area":"agents"},{"id":"2511.03925","title":"Collaborative Agents for Automated Program Repair in Ruby","created":"2025-11-06","cited_by_count":1,"area":"agents"},{"id":"2511.16708","title":"Multi-Agent Code Verification via Information Theory","created":"2025-11-20","cited_by_count":1,"area":"agents"},{"id":"2511.18528","title":"AutoLogger: A Multi-Agent Framework for the End-to-End Automated Logging","created":"2025-11-23","cited_by_count":1,"area":"agents"},{"id":"2605.22526","title":"\"Refactoring Runaway\": Understanding and Mitigating Tangled Refactorings in Coding Agents for Issue Resolution","created":"2026-05-21","cited_by_count":1,"area":"agents"},{"id":"2606.24689","title":"Automated Summarization of Software Documents: An LLM-based Multi-Agent Approach","created":"2026-06-23","cited_by_count":1,"area":"agents"},{"id":"2607.02520","title":"AutoResearch: An Execution-Grounded Multi-Agent Framework for Reliable Research Workflow Automation","created":"2026-05-04","cited_by_count":1,"area":"agents"},{"id":"2607.09553","title":"Writing Bug Reports for Software Repair Agents: What Information Matters Most?","created":"2026-07-10","cited_by_count":1,"area":"agents"},{"id":"2607.12605","title":"Multi-Perspective Agentic Program Repair via Code Property Graphs and Temporal Execution Graphs","created":"2026-07-14","cited_by_count":1,"area":"agents"},{"id":"2608.18092","title":"Position: Multi-Agent Systems Should Prioritize Concurrency Control","created":"2026-06-06","cited_by_count":1,"area":"agents"},{"id":"2609.04167","title":"SWE-Gate: Passing Functional Tests Is Not Enough for Software Engineering Agents","created":"2026-09-03","cited_by_count":1,"area":"agents"},{"id":"2507.01315","title":"Wired for Reuse: Automating Context-Aware Code Adaptation in IDEs via LLM-Based Agent","created":"2025-07-02","cited_by_count":0,"area":"agents"},{"id":"2509.24046","title":"PartnerMAS: An LLM Hierarchical Multi-Agent Framework for Business Partner Selection on High-Dimensional Features","created":"2025-09-28","cited_by_count":0,"area":"agents"},{"id":"2601.08742","title":"Inferring Latent Intentions: Attributional Natural Language Inference in LLM Agents","created":"2026-01-13","cited_by_count":0,"area":"agents"},{"id":"2604.11270","title":"Evaluating LLM Agents on Automated Software Analysis Tasks","created":"2026-04-13","cited_by_count":0,"area":"agents"},{"id":"2606.11976","title":"Exploration Structure in LLM Agents for Multi-File Change Localization","created":"2026-06-10","cited_by_count":0,"area":"agents"},{"id":"2606.21597","title":"ATLAS: Agentic Taxonomy of Large-Scale Software Ecosystems","created":"2026-06-19","cited_by_count":0,"area":"agents"},{"id":"2608.18543","title":"Bridging Search and CRM: Productionizing AI Product Research Agents for Customer Re-Engagement","created":"2026-08-19","cited_by_count":0,"area":"agents"},{"id":"2608.28790","title":"ASTRA - Agentic System for Ticket Resolution and Analysis","created":"2026-08-28","cited_by_count":0,"area":"agents"},{"id":"2609.01603","title":"Efficient SWE Agent Benchmarking via Trajectory-Aware Evaluation","created":"2026-09-01","cited_by_count":0,"area":"agents"},{"id":"2609.28843","title":"Blockchain-Enabled Artificial Intelligence and AI Agents for Secure Data Sharing and Cybersecurity Applications","created":"2026-09-23","cited_by_count":0,"area":"agents"},{"id":"2609.33875","title":"Counterfactual Rollout Replay: Forkable Environments as Free Process Rewards for Software Engineering Agents","created":"2026-09-27","cited_by_count":0,"area":"agents"}],"next_cursor":null}