{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T01:38:00Z","timestamp":1775785080782,"version":"3.50.1"},"reference-count":134,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3651218","type":"journal-article","created":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T18:39:33Z","timestamp":1767638373000},"page":"4840-4863","source":"Crossref","is-referenced-by-count":2,"title":["Agentic AI in Healthcare and Medicine: A Seven-Dimensional Taxonomy for Empirical Evaluation of LLM-Based Agents"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-6435-1988","authenticated-orcid":false,"given":"Shubham","family":"Vatsal","sequence":"first","affiliation":[{"name":"Department of Computer Science, CIMS, New York University, New York, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4078-7491","authenticated-orcid":false,"given":"Harsh","family":"Dubey","sequence":"additional","affiliation":[{"name":"Department of Computer Science, CIMS, New York University, New York, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0082-8364","authenticated-orcid":false,"given":"Aditi","family":"Singh","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Cleveland State University, Cleveland, OH, USA"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"issue":"240","key":"ref2","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref3","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Wei"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1002\/hcs2.61"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-023-02448-8"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3604237.3626869"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1111\/bjet.13370"},{"key":"ref8","article-title":"The prompt report: A systematic survey of prompt engineering techniques","volume-title":"arXiv:2406.06608","author":"Schulhoff","year":"2024"},{"key":"ref9","article-title":"A systematic survey of prompt engineering on vision-language foundation models","author":"Gu","year":"2023","journal-title":"arXiv:2307.12980"},{"key":"ref10","article-title":"A systematic survey of prompt engineering in large language models: Techniques and applications","author":"Sahoo","year":"2024","journal-title":"arXiv:2402.07927"},{"key":"ref11","article-title":"A survey of prompt engineering methods in large language models for different NLP tasks","author":"Vatsal","year":"2024","journal-title":"arXiv:2407.12994"},{"key":"ref12","article-title":"Multilingual prompt engineering in large language models: A survey across NLP tasks","author":"Vatsal","year":"2025","journal-title":"arXiv:2505.11665"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4222-0"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/DSInS64146.2024.10992195"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.5435\/JAAOS-D-23-00474"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06291-2"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.bionlp-1.20"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-63592-2_12"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/s44172-024-00271-8"},{"key":"ref20","article-title":"Capabilities of GPT-4 on medical challenge problems","author":"Nori","year":"2023","journal-title":"arXiv:2303.13375"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.omtn.2023.08.009"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2024.0347"},{"key":"ref23","article-title":"Tree of thoughts: Deliberate problem solving with large language models","author":"Yao","year":"2023","journal-title":"arXiv:2305.10601"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.329"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714877"},{"key":"ref26","article-title":"Zodiac: A cardiologist-level LLM framework for multi-agent diagnostics","author":"Zhou","year":"2024","journal-title":"arXiv:2410.02026"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1161\/JAHA.123.033584"},{"key":"ref28","article-title":"Large language model based multi-agents: A survey of progress and challenges","author":"Guo","year":"2024","journal-title":"arXiv:2402.01680"},{"key":"ref29","article-title":"From LLM reasoning to autonomous AI agents: A comprehensive review","author":"Amine Ferrag","year":"2025","journal-title":"arXiv:2504.19678"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/AIoTC63215.2024.10748304"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s44336-024-00009-2"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.18675"},{"key":"ref33","article-title":"An in-depth survey of large language model-based artificial intelligence agents","author":"Zhao","year":"2023","journal-title":"arXiv:2309.14365"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.539"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3711896.3736561"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3748302"},{"key":"ref37","first-page":"9760","article-title":"A review of prominent paradigms for LLM-based agents: Tool use, planning (including RAG), and feedback learning","volume-title":"Proc. 31st Int. Conf. Comput. Linguistics","author":"Li"},{"key":"ref38","article-title":"Understanding the planning of LLM agents: A survey","author":"Huang","year":"2024","journal-title":"arXiv:2402.02716"},{"key":"ref39","article-title":"Survey on evaluation of LLM-based agents","author":"Yehudai","year":"2025","journal-title":"arXiv:2503.16416"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.147"},{"key":"ref41","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alayrac"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-03423-7"},{"key":"ref43","article-title":"ReAct: Synergizing reasoning and acting in language models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yao"},{"key":"ref44","first-page":"68539","article-title":"Toolformer: Language models can teach themselves to use tools","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Schick"},{"key":"ref45","first-page":"8634","article-title":"Reflexion: Language agents with verbal reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Shinn"},{"key":"ref46","article-title":"Self-consistency improves chain of thought reasoning in language models","author":"Wang","year":"2022","journal-title":"arXiv:2203.11171"},{"key":"ref47","article-title":"Autogen: Enabling next-gen llm applications via multi-agent conversations","volume-title":"Proc. 1st Conf. Lang. Model.","author":"Wu"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.557"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.33"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.103743"},{"key":"ref51","article-title":"DoctorAgent-RL: A multi-agent collaborative reinforcement learning system for multi-turn clinical dialogue","author":"Feng","year":"2025","journal-title":"arXiv:2505.19630"},{"key":"ref52","article-title":"AI hospital: Benchmarking large language models in a multi-agent medical interaction simulator","author":"Fan","year":"2024","journal-title":"arXiv:2402.09742"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.510"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/MIPR67560.2025.00078"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91813-1_8"},{"key":"ref56","article-title":"MedAgent-pro: Towards evidence-based multi-modal medical diagnosis via reasoning agentic workflow","author":"Wang","year":"2025","journal-title":"arXiv:2503.18968"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3698587.3701359"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.54364\/aaiml.2025.51187"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-64430-x"},{"key":"ref60","first-page":"79410","article-title":"Mdagents: An adaptive collaboration of llms for medical decision-making","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"Kim"},{"key":"ref61","article-title":"Agent hospital: A simulacrum of hospital with evolvable medical agents","author":"Li","year":"2024","journal-title":"arXiv:2405.02957"},{"key":"ref62","article-title":"PharmAgents: Building a virtual pharma with large language model agents","author":"Gao","year":"2025","journal-title":"arXiv:2503.22164"},{"key":"ref63","article-title":"TxAgent: An AI agent for therapeutic reasoning across a universe of tools","author":"Gao","year":"2025","journal-title":"arXiv:2503.10970"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.1575"},{"key":"ref65","first-page":"195","article-title":"KG4Diagnosis: A hierarchical multi-agent LLM framework with knowledge graph enhancement for medical diagnosis","volume-title":"Proc. AAAI Bridge Program AI Med. Healthcare","author":"Zuo"},{"key":"ref66","article-title":"MDTeamGPT: A self-evolving LLM-based multi-agent framework for multi-disciplinary team medical consultation","author":"Chen","year":"2025","journal-title":"arXiv:2503.13856"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.2196\/59439"},{"key":"ref68","article-title":"Polaris: A safety-focused LLM constellation architecture for healthcare","author":"Mukherjee","year":"2024","journal-title":"arXiv:2403.13313"},{"key":"ref69","article-title":"Rx strategist: Prescription verification using LLM agents system","author":"Van","year":"2024","journal-title":"arXiv:2409.03440"},{"key":"ref70","article-title":"ClinicalLab: Aligning agents for multi-departmental clinical diagnostics in the real world","author":"Yan","year":"2024","journal-title":"arXiv:2406.13890"},{"key":"ref71","article-title":"Agentic LLM workflows for generating patient-friendly medical reports","volume-title":"arXiv:2408.01112","author":"Sudarshan","year":"2024"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/BigData62323.2024.10825748"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1038\/s43856-025-01283-x"},{"key":"ref74","article-title":"Conversational health agents: A personalized LLM-powered agent framework","author":"Abbasian","year":"2023","journal-title":"arXiv:2310.02374"},{"key":"ref75","article-title":"Exploring LLM multi-agents for ICD coding","author":"Li","year":"2024","journal-title":"arXiv:2406.15363"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.bionlp-1.4"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.1340"},{"key":"ref78","article-title":"Beyond direct diagnosis: LLM-based multi-specialist agent consultation for automatic diagnosis","author":"Wang","year":"2024","journal-title":"arXiv:2401.16107"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1145\/3698587.3701392"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.23919\/SoftCOM62040.2024.10721684"},{"key":"ref81","article-title":"Autonomous multi-modal LLM agents for treatment planning in focused ultrasound ablation surgery","author":"Zhao","year":"2025","journal-title":"arXiv:2505.21418"},{"key":"ref82","article-title":"Script-based dialog policy planning for LLM-powered conversational agents: A basic architecture for an \u2019AI therapist\"","author":"Wasenm\u00fcller","year":"2024","journal-title":"arXiv:2412.15242"},{"key":"ref83","article-title":"Enhancing LLMs for impression generation in radiology reports through a multi-agent system","volume-title":"arXiv:2412.06828","author":"Zeng","year":"2024"},{"key":"ref84","article-title":"PIORS: Personalized intelligent outpatient reception based on large language model with multi-agents medical scenario simulation","author":"Bao","year":"2024","journal-title":"arXiv:2411.13902"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-032-05114-1_35"},{"key":"ref86","article-title":"DrugAgent: Automating AI-aided drug discovery programming through LLM multi-agent collaboration","author":"Liu","year":"2024","journal-title":"arXiv:2411.15692"},{"key":"ref87","article-title":"CT-agent: A multimodal-LLM agent for 3D CT radiology question answering","author":"Mao","year":"2025","journal-title":"arXiv:2505.16229"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-032-06004-4_3"},{"key":"ref89","article-title":"DrugPilot: LLM-based parameterized reasoning agent for drug discovery","author":"Li","year":"2025","journal-title":"arXiv:2505.13940"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ISDFS60797.2024.10527275"},{"key":"ref91","article-title":"LLM agent swarm for hypothesis-driven drug discovery","author":"Song","year":"2025","journal-title":"arXiv:2504.17967"},{"key":"ref92","article-title":"Large language model agent for modular task execution in drug discovery","author":"Ock","year":"2025","journal-title":"arXiv:2507.02925"},{"key":"ref93","article-title":"RAG-enhanced collaborative LLM agents for drug discovery","author":"Lee","year":"2025","journal-title":"arXiv:2502.17506"},{"key":"ref94","article-title":"DrugAgent: Multi-agent large language model-based reasoning for drug-target interaction prediction","author":"Inoue","year":"2024","journal-title":"arXiv:2408.13378"},{"key":"ref95","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Lewis"},{"key":"ref96","first-page":"3929","article-title":"Retrieval augmented language model pre-training","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"1","author":"Guu"},{"key":"ref97","article-title":"Generalization through memorization: Nearest neighbor language models","author":"Khandelwal","year":"2019","journal-title":"arXiv:1911.00172"},{"key":"ref98","article-title":"Memgpt: Towards LLMs as operating systems","author":"Packer","year":"2023","journal-title":"arXiv:2310.08560"},{"key":"ref99","article-title":"Self-RAG: Learning to retrieve, generate, and critique through self-reflection","author":"Asai","year":"2024","journal-title":"arXiv:2310.11511"},{"key":"ref100","article-title":"Mass-editing memory in a transformer","author":"Meng","year":"2022","journal-title":"arXiv:2210.07229"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.348"},{"key":"ref102","article-title":"User interaction patterns and breakdowns in conversing with LLM-powered voice assistants","author":"Mahmood","year":"2023","journal-title":"arXiv:2309.13879"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300234"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.212"},{"key":"ref105","article-title":"Measuring distributional shifts in text: The advantage of language model-based embeddings","author":"Gupta","year":"2023","journal-title":"arXiv:2312.02337"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/SaTML64287.2025.00011"},{"key":"ref107","article-title":"An auditing test to detect behavioral shift in language models","author":"Richter","year":"2024","journal-title":"arXiv:2410.19406"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-06484-1"},{"key":"ref109","article-title":"Constitutional AI: Harmlessness from AI feedback","author":"Bai","year":"2022","journal-title":"arXiv:2212.08073"},{"key":"ref110","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn"},{"key":"ref111","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/SaTML64287.2025.00010"},{"key":"ref113","article-title":"Automatic and universal prompt injection attacks against large language models","author":"Liu","year":"2024","journal-title":"arXiv:2403.04957"},{"key":"ref114","article-title":"Jailbreak attacks and defenses against large language models: A survey","author":"Yi","year":"2024","journal-title":"arXiv:2407.04295"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.trustnlp-main.23"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00524"},{"key":"ref117","article-title":"A survey on fairness in large language models","author":"Li","year":"2023","journal-title":"arXiv:2308.10149"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1126\/science.aax2342"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.570"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-020-00323-1"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1016\/j.healthpol.2024.105152"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-024-01270-x"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-025-01550-0"},{"key":"ref124","article-title":"AgentOrchestra: Orchestrating hierarchical multi-agent intelligence with the Tool-Environment-Agent(TEA) protocol","author":"Zhang","year":"2025","journal-title":"arXiv:2506.12508"},{"key":"ref125","article-title":"AgentNet: Decentralized evolutionary coordination for LLM-based multi-agent systems","author":"Yang","year":"2025","journal-title":"arXiv:2504.00587"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1245"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.677"},{"key":"ref128","article-title":"A conversational artificial intelligence agent for medication reconciliation and review","author":"Deo","year":"2025","journal-title":"MedRxiv"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-024-00832-8"},{"key":"ref130","article-title":"Enhancing clinical trial patient matching through knowledge augmentation and reasoning with multi-agent","author":"Shi","year":"2024","journal-title":"arXiv:2411.14637"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-53081-z"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-67922-y"},{"key":"ref133","article-title":"AgentClinic: A multimodal agent benchmark to evaluate AI in simulated clinical environments","author":"Schmidgall","year":"2024","journal-title":"arXiv:2405.07960"},{"key":"ref134","article-title":"MedAgentBench: A realistic virtual EHR environment to benchmark medical LLM agents","author":"Jiang","year":"2025","journal-title":"arXiv:2501.14654"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11329025.pdf?arnumber=11329025","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T08:12:43Z","timestamp":1768291963000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11329025\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":134,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3651218","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}