{"total":113,"rows":[{"id":"2501.06322","title":"Multi-Agent Collaboration Mechanisms: A Survey of LLMs","created":"2025-01-10","cited_by_count":431,"area":"agents"},{"id":"2602.12670","title":"SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks","created":"2026-02-13","cited_by_count":315,"area":"agents"},{"id":"2410.13185","title":"Chain of Ideas: Revolutionizing Research Via Novel Idea Development with LLM Agents","created":"2024-10-17","cited_by_count":97,"area":"agents"},{"id":"2405.20309","title":"Large Language Models Can Self-Improve At Web Agent Tasks","created":"2024-05-30","cited_by_count":55,"area":"agents"},{"id":"2405.14125","title":"ALI-Agent: Assessing LLMs' Alignment with Human Values via Agent-based Evaluation","created":"2024-05-23","cited_by_count":47,"area":"agents"},{"id":"2405.20267","title":"Auto-Arena: Automating LLM Evaluations with Agent Peer Battles and Committee Discussions","created":"2024-05-30","cited_by_count":42,"area":"agents"},{"id":"2505.07782","title":"MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering","created":"2025-05-12","cited_by_count":41,"area":"agents"},{"id":"2602.06855","title":"AIRS-Bench: a Suite of Tasks for Frontier AI Research Science Agents","created":"2026-02-06","cited_by_count":38,"area":"agents"},{"id":"2502.14074","title":"Investigating Non-Transitivity in LLM-as-a-Judge","created":"2025-02-19","cited_by_count":34,"area":"agents"},{"id":"2505.12923","title":"The Traitors: Deception and Trust in Multi-Agent Language Model Simulations","created":"2025-05-19","cited_by_count":34,"area":"agents"},{"id":"2405.00972","title":"CACTUS: Chemistry Agent Connecting Tool-Usage to Science","created":"2024-05-02","cited_by_count":33,"area":"agents"},{"id":"2412.10270","title":"Cultural Evolution of Cooperation among LLM Agents","created":"2024-12-13","cited_by_count":32,"area":"agents"},{"id":"2504.04310","title":"CO-Bench: Benchmarking Language Model Agents in Algorithm Search for Combinatorial Optimization","created":"2025-04-06","cited_by_count":29,"area":"agents"},{"id":"2506.14852","title":"Agentic Plan Caching: Test-Time Memory for Fast and Cost-Efficient LLM Agents","created":"2025-06-17","cited_by_count":27,"area":"agents"},{"id":"2505.21116","title":"Creativity in LLM-based Multi-Agent Systems: A Survey","created":"2025-05-27","cited_by_count":23,"area":"agents"},{"id":"2505.02847","title":"Sentient Agent as a Judge: Evaluating Higher-Order Social Cognition in Large Language Models","created":"2025-05-01","cited_by_count":21,"area":"agents"},{"id":"2506.07972","title":"HeuriGym: An Agentic Benchmark for LLM-Crafted Heuristics in Combinatorial Optimization","created":"2025-06-09","cited_by_count":21,"area":"agents"},{"id":"2406.13144","title":"DialSim: A Dialogue Simulator for Evaluating Long-Term Multi-Party Dialogue Understanding of Conversational Agents","created":"2024-06-19","cited_by_count":20,"area":"agents"},{"id":"2506.02040","title":"Beyond the Protocol: Unveiling Attack Vectors in the Model Context Protocol (MCP) Ecosystem","created":"2025-05-31","cited_by_count":19,"area":"agents"},{"id":"2602.16873","title":"AdaptOrch: Task-Adaptive Multi-Agent Orchestration in the Era of LLM Performance Convergence","created":"2026-02-18","cited_by_count":17,"area":"agents"},{"id":"2406.11132","title":"RePrompt: Planning by Automatic Prompt Engineering for Large Language Models Agents","created":"2024-06-17","cited_by_count":16,"area":"agents"},{"id":"2601.02695","title":"EvoRoute: Experience-Driven Self-Routing LLM Agent Systems","created":"2026-01-06","cited_by_count":16,"area":"agents"},{"id":"2510.03194","title":"CoDA: Agentic Systems for Collaborative Data Visualization","created":"2025-10-03","cited_by_count":15,"area":"agents"},{"id":"2510.02418","title":"BrowserArena: Evaluating LLM Agents on Real-World Web Navigation Tasks","created":"2025-10-02","cited_by_count":14,"area":"agents"},{"id":"2506.11102","title":"Evolutionary Perspectives on the Evaluation of LLM-Based AI Agents: A Comprehensive Survey","created":"2025-06-06","cited_by_count":13,"area":"agents"},{"id":"2512.17776","title":"DEER: A Benchmark for Evaluating Deep Research Agents on Expert Report Generation","created":"2025-12-19","cited_by_count":12,"area":"agents"},{"id":"2605.26079","title":"Automated Benchmark Auditing for AI Agents and Large Language Models","created":"2026-05-25","cited_by_count":12,"area":"agents"},{"id":"2502.00510","title":"Understanding and Optimizing Agentic Workflows via Shapley value","created":"2025-02-01","cited_by_count":10,"area":"agents"},{"id":"2507.02735","title":"Meta SecAlign: A Secure Foundation LLM Against Prompt Injection Attacks","created":"2025-07-03","cited_by_count":10,"area":"agents"},{"id":"2507.15003","title":"The Rise of AI Teammates in Software Engineering (SE) 3.0: How Autonomous Coding Agents Are Reshaping Software Engineering","created":"2025-07-20","cited_by_count":9,"area":"agents"},{"id":"2510.07307","title":"MLE-Smith: Scaling MLE Tasks with Automated Multi-Agent Pipeline","created":"2025-10-08","cited_by_count":9,"area":"agents"},{"id":"2608.05179","title":"Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap","created":"2026-06-29","cited_by_count":9,"area":"agents"},{"id":"2405.20859","title":"clembench-2024: A Challenging, Dynamic, Complementary, Multilingual Benchmark and Underlying Flexible Framework for LLMs as Multi-Action Agents","created":"2024-05-31","cited_by_count":8,"area":"agents"},{"id":"2510.08847","title":"What Is Your Agent's GPA? A Framework for Evaluating Agent Goal-Plan-Action Alignment","created":"2025-10-09","cited_by_count":8,"area":"agents"},{"id":"2602.02369","title":"Live-Evo: Online Evolution of Agentic Memory from Continuous Feedback","created":"2026-02-02","cited_by_count":8,"area":"agents"},{"id":"2607.02577","title":"Benchmarking the Benchmarks: A Validity Audit of Tool-Calling Evaluation","created":"2026-06-30","cited_by_count":8,"area":"agents"},{"id":"2408.09785","title":"GoNoGo: An Efficient LLM-based Multi-Agent System for Streamlining Automotive Software Release Decision-Making","created":"2024-08-19","cited_by_count":6,"area":"agents"},{"id":"2409.04617","title":"Sparse Rewards Can Self-Train Dialogue Agents","created":"2024-09-06","cited_by_count":6,"area":"agents"},{"id":"2502.16810","title":"AI Realtor: Towards Grounded Persuasive Language Generation for Automated Copywriting","created":"2025-02-24","cited_by_count":6,"area":"agents"},{"id":"2503.00729","title":"CLEA: Closed-Loop Embodied Agent for Enhancing Task Execution in Dynamic Environments","created":"2025-03-02","cited_by_count":6,"area":"agents"},{"id":"2507.05495","title":"Deep Research Comparator: A Platform For Fine-grained Human Annotations of Deep Research Agents","created":"2025-07-07","cited_by_count":6,"area":"agents"},{"id":"2511.21572","title":"BAMAS: Structuring Budget-Aware Multi-Agent Systems","created":"2025-11-26","cited_by_count":6,"area":"agents"},{"id":"2607.13125","title":"Boogu-Image-0.1: Boosting Open Agentic Multimodal Generation via Understanding under a Minimal Budget","created":"2026-07-14","cited_by_count":6,"area":"agents"},{"id":"2506.22957","title":"Agent-to-Agent Theory of Mind: Testing Interlocutor Awareness among Large Language Models","created":"2025-06-28","cited_by_count":5,"area":"agents"},{"id":"2507.02976","title":"How Safe Are AI-Generated Patches? A Large-scale Study on Security Risks in LLM and Agentic Automated Program Repair on SWE-bench","created":"2025-06-30","cited_by_count":5,"area":"agents"},{"id":"2507.13729","title":"AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework","created":"2025-07-18","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":"2603.20324","title":"When Agents Disagree: The Selection Bottleneck in Multi-Agent LLM Pipelines","created":"2026-03-20","cited_by_count":5,"area":"agents"},{"id":"2605.24279","title":"ContextEcho: A Benchmark for Persona Drift in Long Agentic-Coding Sessions","created":"2026-05-22","cited_by_count":5,"area":"agents"},{"id":"2404.08692","title":"Apollonion: Profile-centric Dialog Agent","created":"2024-04-10","cited_by_count":4,"area":"agents"},{"id":"2505.04628","title":"How Social is It? A Benchmark for LLMs' Capabilities in Multi-user Multi-turn Social Agent Tasks","created":"2025-04-04","cited_by_count":4,"area":"agents"},{"id":"2505.23006","title":"A Practical Approach for Building Production-Grade Conversational Agents with Workflow Graphs","created":"2025-05-29","cited_by_count":4,"area":"agents"},{"id":"2510.09021","title":"RefGrader: Automated Grading of Mathematical Competition Proofs using Agentic Workflows","created":"2025-10-10","cited_by_count":4,"area":"agents"},{"id":"2601.17617","title":"Agentic Search in the Wild: Intents and Trajectory Dynamics from 14M+ Real Search Requests","created":"2026-01-24","cited_by_count":4,"area":"agents"},{"id":"2603.00993","title":"CollabEval: Enhancing LLM-as-a-Judge via Multi-Agent Collaboration","created":"2026-03-01","cited_by_count":4,"area":"agents"},{"id":"2604.05339","title":"Human Values Matter: Investigating How Misalignment Shapes Collective Behaviors in LLM Agent Communities","created":"2026-04-07","cited_by_count":4,"area":"agents"},{"id":"2608.11683","title":"FrontierFinance: A Challenging Benchmark for Measuring Frontier Intelligence of Finance Agents","created":"2026-08-12","cited_by_count":4,"area":"agents"},{"id":"2503.16463","title":"Improving Interactive Diagnostic Ability of a Large Language Model Agent Through Clinical Experience Learning","created":"2025-02-24","cited_by_count":3,"area":"agents"},{"id":"2604.03527","title":"Explainable Model Routing for Agentic Workflows","created":"2026-04-04","cited_by_count":3,"area":"agents"},{"id":"2605.08647","title":"AgentCollabBench: Diagnosing When Good Agents Make Bad Collaborators","created":"2026-05-09","cited_by_count":3,"area":"agents"},{"id":"2608.12355","title":"Humans are Missing from AI Coding Agent Research","created":"2026-07-04","cited_by_count":3,"area":"agents"},{"id":"2506.13037","title":"MAGIC: Multi-Agent Argumentation and Grammar Integrated Critiquer","created":"2025-06-16","cited_by_count":2,"area":"agents"},{"id":"2508.03329","title":"Industrial LLM-based Code Optimization under Regulation: A Mixture-of-Agents Approach","created":"2025-08-05","cited_by_count":2,"area":"agents"},{"id":"2511.03051","title":"No-Human in the Loop: Agentic Evaluation at Scale for Recommendation","created":"2025-11-04","cited_by_count":2,"area":"agents"},{"id":"2511.17671","title":"MURMUR: Using cross-user chatter to break collaborative language agents in groups","created":"2025-11-21","cited_by_count":2,"area":"agents"},{"id":"2511.21758","title":"A Longitudinal Measurement of Privacy Policy Evolution for Large Language Models","created":"2025-11-24","cited_by_count":2,"area":"agents"},{"id":"2603.11011","title":"Task-Aware Delegation Cues for LLM Agents","created":"2026-03-11","cited_by_count":2,"area":"agents"},{"id":"2605.02463","title":"When Stress Becomes Signal: Detecting Antifragility-Compatible Regimes in Multi-Agent LLM Systems","created":"2026-05-04","cited_by_count":2,"area":"agents"},{"id":"2605.28158","title":"OR-Space: A Full-Lifecycle Workspace Benchmark for Industrial Optimization Agents","created":"2026-05-27","cited_by_count":2,"area":"agents"},{"id":"2606.05548","title":"ADK Arena: Evaluating Agent Development Kits via LLM-as-a-Developer","created":"2026-06-04","cited_by_count":2,"area":"agents"},{"id":"2606.17541","title":"Offline Preference-Based Trajectory Evaluation","created":"2026-06-16","cited_by_count":2,"area":"agents"},{"id":"2608.21601","title":"K-Bench: measuring model performance on real scientific agent requests","created":"2026-08-21","cited_by_count":2,"area":"agents"},{"id":"2505.22981","title":"Free Lunch for User Experience: Crowdsourcing Agents for Scalable User Studies","created":"2025-05-29","cited_by_count":1,"area":"agents"},{"id":"2508.00632","title":"Multi-Agent Game Generation and Evaluation via Audio-Visual Recordings","created":"2025-08-01","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":"2603.09004","title":"Can AI Agents Generate Microservices? How Far are We?","created":"2026-03-09","cited_by_count":1,"area":"agents"},{"id":"2606.01815","title":"CRAB-Bench: Evaluating LLM Agents under Complex Task Dependencies and Human-aligned User Simulation","created":"2026-06-01","cited_by_count":1,"area":"agents"},{"id":"2608.00794","title":"Measurement Without Validity: The Compounding Reliability Problem in Agentic AI Evaluation","created":"2026-08-01","cited_by_count":1,"area":"agents"},{"id":"2608.04077","title":"FinProBench: Evaluating Financial AI Agents with Role-Grounded Rubrics Derived from Professional Deliverables","created":"2026-08-04","cited_by_count":1,"area":"agents"},{"id":"2608.08852","title":"Findings of the First Teaching Monster Challenge: A Benchmark of Pedagogical Content Knowledge in AI Agents","created":"2026-08-09","cited_by_count":1,"area":"agents"},{"id":"2608.11236","title":"TRACE Bench: Task-driven Roleplay Agentic Checklist Evaluation","created":"2026-07-31","cited_by_count":1,"area":"agents"},{"id":"2608.16551","title":"What to Remember, What to Reveal: Privacy-Aware Memory for Conversational Agents","created":"2026-08-17","cited_by_count":1,"area":"agents"},{"id":"2608.18423","title":"FM-Bench: A Benchmark for Long-Horizon Management with Competing Agents","created":"2026-08-19","cited_by_count":1,"area":"agents"},{"id":"2609.07785","title":"What Does an LLM-Agent Leaderboard Rank Actually Compare?","created":"2026-09-07","cited_by_count":1,"area":"agents"},{"id":"2506.21582","title":"VIDEE: Visual and Interactive Decomposition, Execution, and Evaluation of Text Analytics with Intelligent Agents","created":"2025-06-17","cited_by_count":0,"area":"agents"},{"id":"2512.04702","title":"POLARIS: Is Multi-Agentic Reasoning the Next Wave in Engineering Self-Adaptive Systems?","created":"2025-12-04","cited_by_count":0,"area":"agents"},{"id":"2603.21178","title":"LLM-based Automated Architecture View Generation: Where Are We Now?","created":"2026-03-22","cited_by_count":0,"area":"agents"},{"id":"2604.11655","title":"RPA-Check: A Multi-Stage Automated Framework for Evaluating Dynamic LLM-based Role-Playing Agents","created":"2026-04-13","cited_by_count":0,"area":"agents"},{"id":"2604.26235","title":"LATTICE: Evaluating Decision Support Utility of Crypto Agents","created":"2026-04-29","cited_by_count":0,"area":"agents"},{"id":"2606.00931","title":"CV-Arena: An Open Benchmark for Instructional Computer Vision Problem Solving with Human-AI Collaborative Preferences","created":"2026-05-30","cited_by_count":0,"area":"agents"},{"id":"2606.02951","title":"SCOPE: Real-Time Natural Language Camera Agent at the Edge","created":"2026-06-01","cited_by_count":0,"area":"agents"},{"id":"2606.14397","title":"Running the Gauntlet: Challenging Agentic Tasks","created":"2026-06-12","cited_by_count":0,"area":"agents"},{"id":"2606.16682","title":"Multimodal Evaluator Preference Collapse: Cross-Modal Coupling in Self-Evolving Agents","created":"2026-06-15","cited_by_count":0,"area":"agents"},{"id":"2607.01668","title":"VeriChat: An Agentic Conversational AI Assistant for Hardware Security Verification","created":"2026-07-02","cited_by_count":0,"area":"agents"},{"id":"2607.10789","title":"Imaging-101: Benchmarking LLM Coding Agents on Scientific Computational Imaging","created":"2026-07-12","cited_by_count":0,"area":"agents"},{"id":"2607.13189","title":"RAGthoven at SemEval-2026 Task 1: A Multi-Stage Pipeline Walks Into a Benchmark and Barely Clears the Bar","created":"2026-07-14","cited_by_count":0,"area":"agents"},{"id":"2607.14408","title":"Reward-Free Evolving Agents via Pairwise Validator","created":"2026-07-15","cited_by_count":0,"area":"agents"},{"id":"2608.12831","title":"Fast A/B/n Testing: Exact Multi-Policy Comparison via Tree-Coupled Feedback Sharing","created":"2026-08-13","cited_by_count":0,"area":"agents"},{"id":"2608.21374","title":"LitReview Arena: Evaluating Literature Review Agents with Battle-Style Peer Review Platform","created":"2026-07-01","cited_by_count":0,"area":"agents"},{"id":"2609.00621","title":"Control-Data Flow Separation: Stable Prompt Optimization in Multi-Agent LLMs","created":"2026-09-01","cited_by_count":0,"area":"agents"}],"next_cursor":"100"}