{"total":101,"rows":[{"id":"2405.07960","title":"AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environments","created":"2024-05-13","cited_by_count":231,"area":"agents"},{"id":"2405.02957","title":"Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents","created":"2024-05-05","cited_by_count":218,"area":"agents"},{"id":"2311.17371","title":"Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs","created":"2023-11-29","cited_by_count":114,"area":"agents"},{"id":"2402.09742","title":"AI Hospital: Benchmarking Large Language Models in a Multi-agent Medical Interaction Simulator","created":"2024-02-15","cited_by_count":101,"area":"agents"},{"id":"2407.01603","title":"A Review of Large Language Models and Autonomous Agents in Chemistry","created":"2024-06-26","cited_by_count":99,"area":"agents"},{"id":"2502.11211","title":"A Survey of LLM-based Agents in Medicine: How far are we from Baymax?","created":"2025-02-16","cited_by_count":85,"area":"agents"},{"id":"2402.11443","title":"Benchmark Self-Evolving: A Multi-Agent Framework for Dynamic LLM Evaluation","created":"2024-02-18","cited_by_count":75,"area":"agents"},{"id":"2503.11733","title":"LLM Agents for Education: Advances and Applications","created":"2025-03-14","cited_by_count":59,"area":"agents"},{"id":"2303.17071","title":"DERA: Enhancing Large Language Model Completions with Dialog-Enabled Resolving Agents","created":"2023-03-30","cited_by_count":52,"area":"agents"},{"id":"2405.14751","title":"AGILE: A Novel Reinforcement Learning Framework of LLM Agents","created":"2024-05-23","cited_by_count":45,"area":"agents"},{"id":"2503.22678","title":"Self-Evolving Multi-Agent Simulations for Realistic Clinical Interactions","created":"2025-03-28","cited_by_count":40,"area":"agents"},{"id":"2505.16997","title":"X-MAS: Towards Building Multi-Agent Systems with Heterogeneous LLMs","created":"2025-05-22","cited_by_count":38,"area":"agents"},{"id":"2508.21148","title":"A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers","created":"2025-08-28","cited_by_count":37,"area":"agents"},{"id":"2503.13856","title":"MDTeamGPT: A Self-Evolving LLM-based Multi-Agent Framework for Multi-Disciplinary Team Medical Consultation","created":"2025-03-18","cited_by_count":26,"area":"agents"},{"id":"2605.02240","title":"PhysicianBench: Evaluating LLM Agents in Real-World EHR Environments","created":"2026-05-04","cited_by_count":21,"area":"agents"},{"id":"2502.13957","title":"Supervising the search process produces reliable and generalizable information-seeking agents","created":"2025-02-19","cited_by_count":20,"area":"agents"},{"id":"2412.01605","title":"Medchain: Bridging the Gap Between LLM Agents and Clinical Practice with Interactive Sequence","created":"2024-12-02","cited_by_count":17,"area":"agents"},{"id":"2510.04284","title":"Doctor-R1: Mastering Clinical Inquiry with Experiential Agentic Reinforcement Learning","created":"2025-10-05","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":"2605.18930","title":"OEP: Poisoning Self-Evolving LLM Agents via Locally Correct but Non-Transferable Experiences","created":"2026-05-18","cited_by_count":14,"area":"agents"},{"id":"2502.13010","title":"Agentic Medical Knowledge Graphs Enhance Medical Question Answering: Bridging the Gap Between LLMs and Evolving Medical Knowledge","created":"2025-02-18","cited_by_count":12,"area":"agents"},{"id":"2503.13205","title":"MAP: Evaluation and Multi-Agent Enhancement of Large Language Models for Inpatient Pathways","created":"2025-03-17","cited_by_count":10,"area":"agents"},{"id":"2509.24958","title":"The Dialogue That Heals: A Comprehensive Evaluation of Doctor Agents' Inquiry Capability","created":"2025-09-29","cited_by_count":10,"area":"agents"},{"id":"2510.16499","title":"Automated Composition of Agents: A Knapsack Approach for Agentic Component Selection","created":"2025-10-18","cited_by_count":10,"area":"agents"},{"id":"2511.11306","title":"iMAD: Intelligent Multi-Agent Debate for Efficient and Accurate LLM Inference","created":"2025-11-14","cited_by_count":10,"area":"agents"},{"id":"2505.20824","title":"MedSentry: Understanding and Mitigating Safety Risks in Medical LLM Multi-Agent Systems","created":"2025-05-27","cited_by_count":9,"area":"agents"},{"id":"2601.12259","title":"FutureX-Pro: Extending Future Prediction to High-Value Vertical Domains","created":"2026-01-18","cited_by_count":9,"area":"agents"},{"id":"2505.12442","title":"IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems","created":"2025-05-18","cited_by_count":8,"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":"2602.17692","title":"Agentic Unlearning: When LLM Agent Meets Machine Unlearning","created":"2026-02-06","cited_by_count":8,"area":"agents"},{"id":"2603.05520","title":"Information-Theoretic Privacy Control for Sequential Multi-Agent LLM Systems","created":"2026-02-13","cited_by_count":8,"area":"agents"},{"id":"2606.31179","title":"HealthAgentBench: A Unified Benchmark Suite of Realistic Agentic Healthcare Environments for Challenging Frontier AI Agents","created":"2026-06-30","cited_by_count":8,"area":"agents"},{"id":"2510.08517","title":"CaRT: Teaching LLM Agents to Know When They Know Enough","created":"2025-10-09","cited_by_count":7,"area":"agents"},{"id":"2509.20067","title":"MACD: Multi-Agent Clinical Diagnosis with Self-Learned Knowledge for LLM","created":"2025-09-24","cited_by_count":6,"area":"agents"},{"id":"2601.04861","title":"Orchestrating Intelligence: Confidence-Aware Routing for Efficient Multi-Agent Collaboration across Multi-Scale Models","created":"2026-01-08","cited_by_count":6,"area":"agents"},{"id":"2605.14089","title":"SkillFlow: Flow-Driven Recursive Skill Evolution for Agentic Orchestration","created":"2026-05-13","cited_by_count":6,"area":"agents"},{"id":"2509.24107","title":"Fathom-DeepResearch: Unlocking Long Horizon Information Retrieval and Synthesis for SLMs","created":"2025-09-28","cited_by_count":5,"area":"agents"},{"id":"2511.09804","title":"SlideBot: A Multi-Agent Framework for Generating Informative, Reliable, Multi-Modal Presentations","created":"2025-11-12","cited_by_count":5,"area":"agents"},{"id":"2604.13349","title":"When Less Latent Leads to Better Relay: Information-Preserving Compression for Latent Multi-Agent LLM Collaboration","created":"2026-04-14","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":"2603.26182","title":"ClinicalAgents: Multi-Agent Orchestration for Clinical Decision Making with Dual-Memory","created":"2026-03-27","cited_by_count":4,"area":"agents"},{"id":"2605.25421","title":"HyLaT: Efficient Multi-Agent Communication via Hybrid Latent-Text Protocol","created":"2026-05-25","cited_by_count":4,"area":"agents"},{"id":"2606.01961","title":"AutoMedBench: Towards Medical AutoResearch with Agentic AI Models","created":"2026-06-01","cited_by_count":4,"area":"agents"},{"id":"2606.02568","title":"ClinEnv: An Interactive Multi-Stage Long Horizon EHR Environment for Agents","created":"2026-06-01","cited_by_count":4,"area":"agents"},{"id":"2606.03416","title":"MeDxAgent: Multi-Agent Consultation for Interactive Medical Diagnosis","created":"2026-06-02","cited_by_count":4,"area":"agents"},{"id":"2606.15609","title":"FragFuse: Bypassing Access Control of Large Language Model Agents via Memory-Based Query Fragmentation and Fusion","created":"2026-06-14","cited_by_count":4,"area":"agents"},{"id":"2606.18203","title":"RubricsTree: Scalable and Evolving Open-Ended Evaluation of Personal Health Agents across Health Memory and Medical Skills","created":"2026-06-16","cited_by_count":4,"area":"agents"},{"id":"2508.19163","title":"MATRIX: Multi-Agent simulaTion fRamework for safe Interactions and conteXtual clinical conversational evaluation","created":"2025-08-26","cited_by_count":3,"area":"agents"},{"id":"2512.10195","title":"AutoMedic: An Automated Evaluation Framework for Clinical Conversational Agents with Medical Dataset Grounding","created":"2025-12-11","cited_by_count":3,"area":"agents"},{"id":"2512.17838","title":"ReX-MLE: The Autonomous Agent Benchmark for Medical Imaging Challenges","created":"2025-12-19","cited_by_count":3,"area":"agents"},{"id":"2601.04742","title":"Tool-MAD: A Multi-Agent Debate Framework for Fact Verification with Diverse Tool Augmentation and Adaptive Retrieval","created":"2026-01-08","cited_by_count":3,"area":"agents"},{"id":"2602.08013","title":"Small Agent Group is the Future of Digital Health","created":"2026-02-08","cited_by_count":3,"area":"agents"},{"id":"2602.11574","title":"Learning to Configure Agentic AI Systems","created":"2026-02-12","cited_by_count":3,"area":"agents"},{"id":"2603.02960","title":"Architecting Trust in Artificial Epistemic Agents","created":"2026-03-03","cited_by_count":3,"area":"agents"},{"id":"2604.12262","title":"CascadeDebate: Multi-Agent Deliberation for Cost-Aware LLM Cascades","created":"2026-04-14","cited_by_count":3,"area":"agents"},{"id":"2605.18067","title":"PPAI: Enabling Personalized LLM Agent Interoperability for Collaborative Edge Intelligence","created":"2026-05-18","cited_by_count":3,"area":"agents"},{"id":"2608.04893","title":"When Does Latent Communication Pay? A Causal Audit of Relayed KV Caches in Multi-Agent LLMs","created":"2026-08-05","cited_by_count":3,"area":"agents"},{"id":"2404.04285","title":"MIMIR: A Streamlined Platform for Personalized Agent Tuning in Domain Expertise","created":"2024-04-03","cited_by_count":2,"area":"agents"},{"id":"2505.23055","title":"CDR-Agent: Intelligent Selection and Execution of Clinical Decision Rules Using Large Language Model Agents","created":"2025-05-29","cited_by_count":2,"area":"agents"},{"id":"2507.02616","title":"DynamiCare: A Dynamic Multi-Agent Framework for Interactive and Open-Ended Medical Decision-Making","created":"2025-07-03","cited_by_count":2,"area":"agents"},{"id":"2509.11078","title":"Patient-Zero: Scaling Synthetic Patient Agents to Real-World Distributions without Real Patient Data","created":"2025-09-14","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":"2602.00966","title":"Symphony-Coord: Adaptive Routing for Multi-Agent LLM Systems","created":"2026-02-01","cited_by_count":2,"area":"agents"},{"id":"2604.22861","title":"IntrAgent: An LLM Agent for Content-Grounded Information Retrieval through Literature Review","created":"2026-04-23","cited_by_count":2,"area":"agents"},{"id":"2605.10064","title":"MAGE: Multi-Agent Self-Evolution with Co-Evolutionary Knowledge Graphs","created":"2026-05-11","cited_by_count":2,"area":"agents"},{"id":"2605.13542","title":"RealICU: Do LLM Agents Understand Long-Context ICU Data? A Benchmark Beyond Behavior Imitation","created":"2026-05-13","cited_by_count":2,"area":"agents"},{"id":"2505.21757","title":"BehaviorSFT: Behavioral Token Conditioning for Clinical Agents Across the Proactivity Spectrum","created":"2025-05-27","cited_by_count":1,"area":"agents"},{"id":"2602.18460","title":"The Doctor Will (Still) See You Now: On the Structural Limits of Agentic AI in Healthcare","created":"2026-02-06","cited_by_count":1,"area":"agents"},{"id":"2603.24973","title":"Belief-Driven Multi-Agent Collaboration via Approximate Perfect Bayesian Equilibrium for Social Simulation","created":"2026-03-26","cited_by_count":1,"area":"agents"},{"id":"2604.00137","title":"Open, Reliable, and Collective: A Community-Driven Framework for Tool-Using AI Agents","created":"2026-03-31","cited_by_count":1,"area":"agents"},{"id":"2605.07058","title":"MedExAgent: Training LLM Agents to Ask, Examine, and Diagnose in Noisy Clinical Environments","created":"2026-05-08","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":"2606.18068","title":"Agentic AI-based Framework for Mitigating Premature Diagnostic Handoff and Silent Hallucination in Healthcare Applications","created":"2026-06-16","cited_by_count":1,"area":"agents"},{"id":"2607.26836","title":"Before Agents Speak: Pre-hoc Failure Risk Inference in Multi-Agent Systems","created":"2026-07-29","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":"2608.22752","title":"The Compaction Cliff in Long-Running AI Agent Memory","created":"2026-08-24","cited_by_count":1,"area":"agents"},{"id":"2608.27338","title":"One Model, Many Minds: Unlocking Multi-Agent Synergy in a Single Agent via Mixture of Roles","created":"2026-08-27","cited_by_count":1,"area":"agents"},{"id":"2609.15161","title":"EMR: Self-Evolving Medical Multi-Agent System via Experience Mining and Reuse","created":"2026-09-14","cited_by_count":1,"area":"agents"},{"id":"2507.21159","title":"MAC: Masked Agent Collaboration Boosts Large Language Model Medical Decision-Making","created":"2025-07-25","cited_by_count":0,"area":"agents"},{"id":"2510.26352","title":"The Geometry of Dialogue: Graphing Language Models to Reveal Synergistic Teams for Multi-Agent Collaboration","created":"2025-10-30","cited_by_count":0,"area":"agents"},{"id":"2602.11220","title":"Patch the Distribution Mismatch: RL Rewriting Agent for Stable Off-Policy SFT","created":"2026-02-11","cited_by_count":0,"area":"agents"},{"id":"2603.09157","title":"Real-Time Trust Verification for Safe Agentic Actions using TrustBench","created":"2026-03-10","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":"2605.27621","title":"Agents that Matter: Optimizing Multi-Agent LLMs via Removal-Based Attribution","created":"2026-05-26","cited_by_count":0,"area":"agents"},{"id":"2606.01434","title":"DrugClaw and DrugAudit: A Primary-Source-Grounded Agent and Authority-Aware Benchmark for Drug-Information Question Answering","created":"2026-05-31","cited_by_count":0,"area":"agents"},{"id":"2606.21959","title":"OpenBioRQ: Unsolved Biomedical Research Questions for Agents","created":"2026-06-20","cited_by_count":0,"area":"agents"},{"id":"2606.25651","title":"MedGuards: Multi-Agent System for Reliable Medical Error Detection and Correction","created":"2026-06-24","cited_by_count":0,"area":"agents"},{"id":"2607.02879","title":"MedCalc-Pro: Solving Complex Medical Calculations with LLM Agents","created":"2026-07-03","cited_by_count":0,"area":"agents"},{"id":"2607.15314","title":"Cura 1T: Specialized Model for Agentic Healthcare","created":"2026-07-15","cited_by_count":0,"area":"agents"},{"id":"2607.21625","title":"Trajectory-Aware Retrieval Agents for Temporal Decision- Making","created":"2026-07-07","cited_by_count":0,"area":"agents"},{"id":"2608.03744","title":"Agents Catching Agents: Shortcut Cascades and Benchmark Gaming in Clinical Multi-Agent Systems","created":"2026-08-04","cited_by_count":0,"area":"agents"},{"id":"2608.10579","title":"Agentic Instruction Data Selection: Let DataMaster Interpret Your Intent","created":"2026-08-11","cited_by_count":0,"area":"agents"},{"id":"2609.01045","title":"AgentFactory: Towards Automated Agentic System Design and Optimization","created":"2026-09-01","cited_by_count":0,"area":"agents"},{"id":"2609.05069","title":"A Structured Debate-Mixture-of-Agents Framework for Complex Clinical Diagnostic Decision Support","created":"2026-09-04","cited_by_count":0,"area":"agents"},{"id":"2609.21527","title":"OpenMAS-GCom. A Diagnostic Benchmark for Graph-enhanced Multi-Agent Systems","created":"2026-09-18","cited_by_count":0,"area":"agents"},{"id":"2609.36505","title":"BRIDGE: Bilevel Retrieval-Credit-Aware Agentic Reinforcement Learning","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2609.38661","title":"EvoSteer: Online Self-Evolving Graph Orchestration via Reference-Anchored Credit Assignment","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2610.01042","title":"Beyond Final Accuracy: Auditing Communication in LLM Multi-Agent Systems","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.07570","title":"Unanimously Wrong: Certified Abstention from How Medical LLM Consensus Forms","created":"2026-10-06","cited_by_count":0,"area":"agents"},{"id":"2610.08820","title":"Task-Oriented Key-Layer KV Communication for Efficient Latent Multi-Agent Collaboration","created":"2026-09-24","cited_by_count":0,"area":"agents"}],"next_cursor":"100"}