{"total":125,"rows":[{"id":"2307.07924","title":"ChatDev: Communicative Agents for Software Development","created":"2023-07-16","cited_by_count":919,"area":"agents"},{"id":"2308.07201","title":"ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate","created":"2023-08-14","cited_by_count":742,"area":"agents"},{"id":"2310.11667","title":"SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents","created":"2023-10-18","cited_by_count":367,"area":"agents"},{"id":"2309.17288","title":"AutoAgents: A Framework for Automatic Agent Generation","created":"2023-09-29","cited_by_count":216,"area":"agents"},{"id":"2401.05507","title":"InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks","created":"2024-01-10","cited_by_count":140,"area":"agents"},{"id":"2408.00989","title":"On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty Agents","created":"2024-08-02","cited_by_count":99,"area":"agents"},{"id":"2403.08715","title":"SOTOPIA-$\\pi$: Interactive Learning of Socially Intelligent Language Agents","created":"2024-03-13","cited_by_count":93,"area":"agents"},{"id":"2312.17025","title":"Experiential Co-Learning of Software-Developing Agents","created":"2023-12-28","cited_by_count":57,"area":"agents"},{"id":"2401.16788","title":"Can Large Language Models be Trusted for Evaluation? Scalable Meta-Evaluation of LLMs as Evaluators via Agent Debate","created":"2024-01-30","cited_by_count":41,"area":"agents"},{"id":"2402.16499","title":"LLMArena: Assessing Capabilities of Large Language Models in Dynamic Multi-Agent Environments","created":"2024-02-26","cited_by_count":36,"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":"2504.03274","title":"Do Large Language Models Solve the Problems of Agent-Based Modeling? A Critical Review of Generative Social Simulations","created":"2025-04-04","cited_by_count":28,"area":"agents"},{"id":"2602.11103","title":"GameDevBench: Evaluating Agentic Capabilities Through Game Development","created":"2026-02-11","cited_by_count":28,"area":"agents"},{"id":"2410.07672","title":"MACPO: Weak-to-Strong Alignment via Multi-Agent Contrastive Preference Optimization","created":"2024-10-10","cited_by_count":22,"area":"agents"},{"id":"2403.19305","title":"MATEval: A Multi-Agent Discussion Framework for Advancing Open-Ended Text Evaluation","created":"2024-03-28","cited_by_count":20,"area":"agents"},{"id":"2405.16334","title":"Devil's Advocate: Anticipatory Reflection for LLM Agents","created":"2024-05-25","cited_by_count":17,"area":"agents"},{"id":"2601.05111","title":"Agent-as-a-Judge","created":"2026-01-08","cited_by_count":17,"area":"agents"},{"id":"2602.14878","title":"Model Context Protocol (MCP) Tool Descriptions Are Smelly! Towards Improving AI Agent Efficiency with Augmented MCP Tool Descriptions","created":"2026-02-16","cited_by_count":17,"area":"agents"},{"id":"2406.00252","title":"Towards Rationality in Language and Multimodal Agents: A Survey","created":"2024-06-01","cited_by_count":16,"area":"agents"},{"id":"2412.04494","title":"MAG-V: A Multi-Agent Framework for Synthetic Data Generation and Verification","created":"2024-11-28","cited_by_count":12,"area":"agents"},{"id":"2604.18240","title":"AJ-Bench: Benchmarking Agent-as-a-Judge for Environment-Aware Evaluation","created":"2026-04-20","cited_by_count":12,"area":"agents"},{"id":"2605.06635","title":"Cited but Not Verified: Parsing and Evaluating Source Attribution in LLM Deep Research Agents","created":"2026-05-07","cited_by_count":12,"area":"agents"},{"id":"2308.12519","title":"Rational Decision-Making Agent with Internalized Utility Judgment","created":"2023-08-24","cited_by_count":11,"area":"agents"},{"id":"2505.19477","title":"Judging with Many Minds: Do More Perspectives Mean Less Prejudice? On Bias Amplifications and Resistance in Multi-Agent Based LLM-as-Judge","created":"2025-05-26","cited_by_count":11,"area":"agents"},{"id":"2511.13410","title":"Mem-PAL: Towards Memory-based Personalized Dialogue Assistants for Long-term User-Agent Interaction","created":"2025-11-17","cited_by_count":11,"area":"agents"},{"id":"2509.19236","title":"AgentInit: Initializing LLM-based Multi-Agent Systems via Diversity and Expertise Orchestration for Effective and Efficient Collaboration","created":"2025-09-23","cited_by_count":10,"area":"agents"},{"id":"2605.19769","title":"OpenComputer: Verifiable Software Worlds for Computer-Use Agents","created":"2026-05-19","cited_by_count":10,"area":"agents"},{"id":"2605.17076","title":"S-Bus: Automatic Read-Set Reconstruction for Multi-Agent LLM State Coordination","created":"2026-05-16","cited_by_count":8,"area":"agents"},{"id":"2602.18710","title":"Many AI Analysts, One Dataset: Navigating the Agentic Data Science Multiverse","created":"2026-02-21","cited_by_count":7,"area":"agents"},{"id":"2606.29920","title":"Can LLM-as-a-Judge Reliably Verify Rubrics in Agentic Scenarios?","created":"2026-06-29","cited_by_count":7,"area":"agents"},{"id":"2608.04205","title":"MatrAIx: Simulating the World with 8.3 Billion Persona Agents","created":"2026-08-04","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":"2601.04790","title":"Belief in Authority: Impact of Authority in Multi-Agent Evaluation Framework","created":"2026-01-08","cited_by_count":6,"area":"agents"},{"id":"2603.23806","title":"Willful Disobedience: Automatically Detecting Failures in Agentic Traces","created":"2026-03-25","cited_by_count":6,"area":"agents"},{"id":"2607.22368","title":"Do Agent Benchmarks Measure Capability? Protocol Validity in the Age of Agentic AI","created":"2026-07-24","cited_by_count":6,"area":"agents"},{"id":"2606.17698","title":"EComAgentBench: Benchmarking Shopping Agents on Long-Horizon Tasks with Distributed Hidden Intent","created":"2026-06-16","cited_by_count":5,"area":"agents"},{"id":"2608.23564","title":"SWE Refactor Bench: Can Coding Agents Complete a Long-Horizon, Whole-Repository Stack Migration?","created":"2026-08-24","cited_by_count":5,"area":"agents"},{"id":"2508.02013","title":"SpeechRole: A Large-Scale Dataset and Benchmark for Evaluating Speech Role-Playing Agents","created":"2025-08-04","cited_by_count":4,"area":"agents"},{"id":"2510.07309","title":"Agent Bain vs. Agent McKinsey: A New Text-to-SQL Benchmark for the Business Domain","created":"2025-10-08","cited_by_count":4,"area":"agents"},{"id":"2603.17417","title":"Is Your LLM-as-a-Recommender Agent Trustable? LLMs' Recommendation is Easily Hacked by Biases (Preferences)","created":"2026-03-18","cited_by_count":4,"area":"agents"},{"id":"2604.10741","title":"Deep-Reporter: Deep Research for Grounded Multimodal Long-Form Generation","created":"2026-04-12","cited_by_count":4,"area":"agents"},{"id":"2412.13520","title":"ROMAS: A Role-Based Multi-Agent System for Database monitoring and Planning","created":"2024-12-18","cited_by_count":3,"area":"agents"},{"id":"2501.15826","title":"MADP: Multi-Agent Deductive Planning for Enhanced Cognitive-Behavioral Mental Health Question Answer","created":"2025-01-27","cited_by_count":3,"area":"agents"},{"id":"2505.16281","title":"HiMATE: A Hierarchical Multi-Agent Framework for Machine Translation Evaluation","created":"2025-05-22","cited_by_count":3,"area":"agents"},{"id":"2510.16194","title":"Towards Automatic Evaluation and Selection of PHI De-identification Models via Multi-Agent Collaboration","created":"2025-10-17","cited_by_count":3,"area":"agents"},{"id":"2601.07477","title":"JudgeFlow: Agentic Workflow Optimization via Block Judge","created":"2026-01-12","cited_by_count":3,"area":"agents"},{"id":"2602.15219","title":"Multi-Agent Home Energy Management Assistant","created":"2026-02-16","cited_by_count":3,"area":"agents"},{"id":"2603.04582","title":"Self-Attribution Bias: When AI Monitors Go Easy on Themselves","created":"2026-03-04","cited_by_count":3,"area":"agents"},{"id":"2605.26144","title":"VISTA: An End-to-End Benchmark for Visual Spec-to-Web-App Coding Agents","created":"2026-05-22","cited_by_count":3,"area":"agents"},{"id":"2607.21962","title":"Ground Truth First: A Longitudinal Evaluation Instrument for Agent Memory, and the Tenure Crossover in Memory-Architecture Rankings","created":"2026-07-24","cited_by_count":3,"area":"agents"},{"id":"2608.02827","title":"Emergence of Biased Consensus in Multi-Agent LLM Debates","created":"2026-08-03","cited_by_count":3,"area":"agents"},{"id":"2609.02246","title":"LLM-as-a-Judge Is Not an Oracle: Why Self-Improving Agents Need Deterministic Guardrails","created":"2026-09-02","cited_by_count":3,"area":"agents"},{"id":"2609.12191","title":"GAUGE: When Not to Trust LLM-as-a-Judge in User-Simulated Evaluation of Task-Oriented Agents","created":"2026-09-10","cited_by_count":3,"area":"agents"},{"id":"2403.09567","title":"Enhancing Trust in Autonomous Agents: An Architecture for Accountability and Explainability through Blockchain and Large Language Models","created":"2024-03-14","cited_by_count":2,"area":"agents"},{"id":"2507.08038","title":"AblationBench: Evaluating Automated Planning of Ablations in Empirical AI Research","created":"2025-07-09","cited_by_count":2,"area":"agents"},{"id":"2510.05188","title":"Plug-and-Play Dramaturge: A Divide-and-Conquer Approach for Iterative Narrative Script Refinement via Collaborative LLM Agents","created":"2025-10-06","cited_by_count":2,"area":"agents"},{"id":"2602.06486","title":"JADE: Expert-Grounded Dynamic Evaluation for Open-Ended Professional Tasks","created":"2026-02-06","cited_by_count":2,"area":"agents"},{"id":"2604.19548","title":"Taming Actor-Observer Asymmetry in Agents via Dialectical Alignment","created":"2026-04-21","cited_by_count":2,"area":"agents"},{"id":"2604.20548","title":"Enhancing Research Idea Generation through Combinatorial Innovation and Multi-Agent Iterative Search Strategies","created":"2026-04-22","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":"2606.04296","title":"The Saturation Trap and the Subjectivity of Intervention Timing: Why Affect-Based Triggers and LLM Judges Fail to Time Interventions on Autonomous Agents","created":"2026-06-02","cited_by_count":2,"area":"agents"},{"id":"2606.20470","title":"Analyzing Defensive Misdirection Against Model-Guided Automated Attacks on Agentic AI Systems","created":"2026-06-18","cited_by_count":2,"area":"agents"},{"id":"2606.23195","title":"Memory Contagion: Cross-Temporal Propagation of Evaluator Bias via Agent Memory","created":"2026-06-22","cited_by_count":2,"area":"agents"},{"id":"2607.19409","title":"FORCE-Bench: A Benchmark, Dataset, and Evaluation Harness for Agentic AI in Enterprise Finance","created":"2026-07-11","cited_by_count":2,"area":"agents"},{"id":"2608.26623","title":"AgentJudgeBench: A Multi-Difficulty Benchmark for Evaluating LLM Judges on Agentic Tool-Calling","created":"2026-08-27","cited_by_count":2,"area":"agents"},{"id":"2609.00038","title":"trajectory-judge: What Outcome-Only LLM Judges Miss on Agent Trajectories","created":"2026-08-29","cited_by_count":2,"area":"agents"},{"id":"2609.17989","title":"Whom Do AI Agents Work For? Role Assignment Induces Sponsorship Bias in LLM Recommenders","created":"2026-09-16","cited_by_count":2,"area":"agents"},{"id":"2409.14371","title":"The Ability of Large Language Models to Evaluate Constraint-satisfaction in Agent Responses to Open-ended Requests","created":"2024-09-22","cited_by_count":1,"area":"agents"},{"id":"2411.16077","title":"SAGEval: The frontiers of Satisfactory Agent based NLG Evaluation for reference-free open-ended text","created":"2024-11-25","cited_by_count":1,"area":"agents"},{"id":"2503.20028","title":"OmniNova:A General Multimodal Agent Framework","created":"2025-03-25","cited_by_count":1,"area":"agents"},{"id":"2507.23633","title":"MemoCue: Empowering LLM-Based Agents for Human Memory Recall via Strategy-Guided Querying","created":"2025-07-31","cited_by_count":1,"area":"agents"},{"id":"2602.11238","title":"SurveyLens: A Discipline-Aware Benchmark for Automatic Survey Generation","created":"2026-02-11","cited_by_count":1,"area":"agents"},{"id":"2603.00724","title":"RLAR: An Agentic Reward System for Multi-task Reinforcement Learning on Large Language Models","created":"2026-02-28","cited_by_count":1,"area":"agents"},{"id":"2603.20884","title":"MemoNoveltyAgent: A Historical Research Memory-Aware Agent Workflow for Paper Novelty Assessment","created":"2026-03-21","cited_by_count":1,"area":"agents"},{"id":"2604.05157","title":"IntentScore: Intent-Conditioned Action Evaluation for Computer-Use Agents","created":"2026-04-06","cited_by_count":1,"area":"agents"},{"id":"2605.15581","title":"STAR: A Stage-attributed Triage and Repair framework for RCA Agents in Microservices","created":"2026-05-15","cited_by_count":1,"area":"agents"},{"id":"2605.17554","title":"Evaluating Deep Research Agents on Expert Consulting Work: A Benchmark with Verifiers, Rubrics, and Cognitive Traps","created":"2026-05-17","cited_by_count":1,"area":"agents"},{"id":"2605.20312","title":"Pramana: A Protocol-Layer Treatment of Claim Verification in Autonomous Agent Networks","created":"2026-05-19","cited_by_count":1,"area":"agents"},{"id":"2606.10296","title":"The Confident Liar: Diagnosing Multi-Agent Debate with Log-Probabilities and LLM-as-Judge","created":"2026-06-09","cited_by_count":1,"area":"agents"},{"id":"2606.20724","title":"When Web Agents Finish but Still Fail: Reproducible Triggers and Trace Diagnostics for Parallel Web Exploration","created":"2026-06-16","cited_by_count":1,"area":"agents"},{"id":"2607.07436","title":"The Blind Curator: How a Biased Judge Silently Disables Skill Retirement in Self-Evolving Agents","created":"2026-07-08","cited_by_count":1,"area":"agents"},{"id":"2607.27942","title":"Scaling LLM-Driven Multi-Agent Systems: Design Principles and Architectural Scalability Analysis","created":"2026-07-30","cited_by_count":1,"area":"agents"},{"id":"2608.09855","title":"The Greatness of Science Cannot Be Planned: Agentic Auto-Research is Fuzz Testing","created":"2026-08-10","cited_by_count":1,"area":"agents"},{"id":"2608.13564","title":"Inducing Reward-Free Judging Rubrics that Reduce Over-Crediting in Agent Evaluation","created":"2026-06-25","cited_by_count":1,"area":"agents"},{"id":"2608.25937","title":"Candidate supply and answer selection shape the value of LLM judging in multi-agent systems","created":"2026-08-26","cited_by_count":1,"area":"agents"},{"id":"2609.07713","title":"The Emerging AI Paper-Review Arms Race: Adversarial Co-Evolution in Scholarly Publishing","created":"2026-09-07","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":"2609.22086","title":"Designer-RSI: Evolving Procedural Memory from User Traffic for Agentic Graphic Design","created":"2026-09-18","cited_by_count":1,"area":"agents"},{"id":"2609.30345","title":"Coding Agents Aren't Enough! Evaluating an Enterprise Security Brain for Agentic Cloud Investigations","created":"2026-09-24","cited_by_count":1,"area":"agents"},{"id":"2512.01089","title":"CodeDistiller: Automatically Generating Code Libraries for Scientific Coding Agents","created":"2025-11-30","cited_by_count":0,"area":"agents"},{"id":"2602.17990","title":"WorkflowPerturb: Calibrated Stress Tests for Evaluating Multi-Agent Workflow Metrics","created":"2026-02-20","cited_by_count":0,"area":"agents"},{"id":"2604.00477","title":"Logarithmic Scores, Power-Law Discoveries: Disentangling Measurement from Coverage in Agent-Based Evaluation","created":"2026-04-01","cited_by_count":0,"area":"agents"},{"id":"2604.27271","title":"Frame Entrepreneurs in an AI Agent Community: Concentrated Identity-Claim Production on Moltbook","created":"2026-04-29","cited_by_count":0,"area":"agents"},{"id":"2605.17041","title":"Agentic AI Translate: An Agentic Translator Prototype for Translation as Communication Design","created":"2026-05-16","cited_by_count":0,"area":"agents"},{"id":"2605.24699","title":"MDIA: A Multi-Agent Diagnostic Intelligence Pipeline on HealthBench Professional","created":"2026-05-23","cited_by_count":0,"area":"agents"},{"id":"2606.18976","title":"CAPRA: Scaling Feedback on Software Architecture Deliverables with a Multi-Agent LLM System","created":"2026-06-17","cited_by_count":0,"area":"agents"},{"id":"2606.25361","title":"Memory Makes the Difference: Evaluating How Different Memory Roles Shape Conversational Agents","created":"2026-06-24","cited_by_count":0,"area":"agents"},{"id":"2607.18529","title":"EduPanel: A Three-Agent LLM Judge for Teaching Videos -- Reliability, Complementarity, and Human Trust Calibration","created":"2026-07-20","cited_by_count":0,"area":"agents"},{"id":"2607.20510","title":"Telco-GAIA: Bilingual Benchmark for Agents in Telecom Domain","created":"2026-07-04","cited_by_count":0,"area":"agents"},{"id":"2608.03018","title":"UrbanAgent: A Tool-Augmented Agent for Cross-System Urban Tasks","created":"2026-08-04","cited_by_count":0,"area":"agents"}],"next_cursor":"100"}