EHRAgent: Code Empowers Large Language Models for Few-shot Complex Tabular Reasoning on Electronic Health Records
Open accessAbstract
Clinicians often rely on data engineers to retrieve complex patient information from electronic health record (EHR) systems, a process that is both inefficient and time-consuming. We propose EHRAgent, a large language model (LLM) agent empowered with accumulative domain knowledge and robust coding capability. EHRAgent enables autonomous code generation and execution to facilitate clinicians in directly interacting with EHRs using natural language. Specifically, we formulate a multi-tabular reasoning task based on EHRs as a tool-use planning process, efficiently decomposing a complex task into a sequence of manageable actions with external toolsets. We first inject relevant medical information to enable EHRAgent to effectively reason about the given query, identifying and extracting the required records from the appropriate tables. By integrating interactive coding and execution feedback, EHRAgent then effectively learns from error messages and iteratively improves its originally generated code. Experiments on three real-world EHR datasets show that EHRAgent outperforms the strongest baseline by up to 29.6% in success rate, verifying its strong capacity to tackle complex clinical tasks with minimal demonstrations.
Verifying this paper
8 of 9 steps done · this page updates itself — you can leave and come back
- Registry recordVerified
- Full textRead the full text
- Reference list66 references found
- Reference checkChecking each cited work — 69 of 69
- StatisticsNeeds the full text
- ClaimsNeeds the full text
- Cited sourcesNeeds claims to check
- Self-checkNeeds the full text
- VerificationFindings verified
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Similarity-based memory retrieval is a scalable and widely adopted strategy across LLM-based agents.
“we first clarify that similarity-based memory retrieval is a scalable and widely adopted strategy across LLM-based agents (e.g., RAP [20], EHR Agent [29]).”
From Memory Injection Attacks on LLM Agents via Query-Only Interaction (2025) · cites this paper as [29]
The “Demonstration Optimization through Long-Term Memory” section describes EHRAgent retrieving the most relevant past examples using question similarity, so the paper supports EHR Agent as an example of similarity-based memory retrieval. It does not establish that this strategy is scalable or widely adopted across LLM-based agents; no page number is available in our copy. (LLM, conf=0.86)
Experimental — accuracy not yet measuredStructured EHR data can be summarized using general-purpose LLMs like Llama-3.
“while structured EHR data can be summarized using general-purpose LLMs78 like Llama-379.”
From MoMA: a mixture-of-multimodal-agents architecture for enhancing clinical prediction modelling (2025) · cites this paper as [78]
The Experiment Setup and Conclusion describe an LLM-based agent that answers questions using structured EHR tables. They do not establish that general-purpose LLMs summarize structured EHR data; the paper studies multi-table question answering with code execution instead. Llama-3 has a separate citation in the citing sentence. (LLM, conf=0.78)
Experimental — accuracy not yet measuredCoding agents have been applied to offensive security, theorem proving, and clinical tasks.
“Coding agents have also been applied to offensive security [11, 37, 60], theorem proving [44], and clinical tasks [38, 43, 52].”
From SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering (2024) · cites this paper as [38]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
(2001) · The Lancet · doi:10.1016/s0140-6736(01)05333-8 · Cited by 8,217
MIMIC-III, a freely accessible critical care database
Johnson, A. E. W., Pollard, T. J., Shen, L., Lehman, L.-W. H., Feng, M., Ghassemi, M., Moody, B., Szolovits, P., Anthony Celi, L., & Mark, R. G. (2016) · Scientific Data · doi:10.1038/sdata.2016.35 · Cited by 8,141 · cited 2× · see citing works
“To address these limitations, we propose EHRAgent , an autonomous LLM agent with exter-nal tools and code interface for improved multi-tabular reasoning across EHRs.”
BackgroundMethodChain-Of-Thought Prompting Elicits Reasoning in Large Language Models
Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q. V., & Zhou, D. (2022) · Advances in Neural Information Processing Systems 35 · doi:10.52202/068431-1800 · Cited by 4,505 · cited 2× · see citing works
“The disconnection between plan generation and execution, however, prevents LLM agents from effectively and efficiently mitigating error propagation and learning from environmental feedback (Qiao et al., 2023; Shinn et al., 2023; Yang et al., 2023 In such cases, it is generally preferable to…”
BackgroundLlama 2: Open Foundation and Fine-Tuned Chat Models
Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Babaei, Y., Bashlykov, N., Batra, S., Bhargava, P., Bhosale, S., et al. (2023) · arXiv · doi:10.48550/arxiv.2307.09288 · Cited by 2,604 · see citing works
Foundation models for generalist medical artificial intelligence
Moor, M., Banerjee, O., Abad, Z. S. H., Krumholz, H. M., Leskovec, J., Topol, E. J., & Rajpurkar, P. (2023) · Nature · doi:10.1038/s41586-023-05881-4 · Cited by 2,028 · cited 1× · see citing works
“Large language models (LLMs) (OpenAI, 2023; Anil et al., 2023) bring us one step closer to autonomous agents with extensive knowledge and substantial instruction-following abilities from di-a et al., 2017) and SPIDER (Yu et al., 2018), multi-tabular reasoning tasks within EHRs (orange) typically…”
BackgroundPollard, T. J., Johnson, A. E. W., Raffa, J. D., Celi, L. A., Mark, R. G., & Badawi, O. (2018) · Scientific Data · doi:10.1038/sdata.2018.178 · Cited by 1,993 · cited 1× · see citing works
“We translate the EHR question-answering problem into a tool-use planning process – generating, executing, debugging, and optimizing a sequence of code-based actions.”
MethodA survey on large language model based autonomous agents
Wang, L., Ma, C., Feng, X., Zhang, Z., Yang, H., Zhang, J., Chen, Z., Tang, J., Chen, X., Lin, Y., et al. (2024) · Frontiers of Computer Science · doi:10.1007/s11704-024-40231-1 · Cited by 1,941 · see citing works
Self-citationTree of Thoughts: Deliberate Problem Solving with Large Language Models
Yao, S., Yu, D., Zhao, J., Shafran, I., Griffiths, T. L., Cao, Y., & Narasimhan, K. (2023) · arXiv · doi:10.48550/arxiv.2305.10601 · Cited by 1,158 · cited 1× · see citing works
“The disconnection between plan generation and execution, however, prevents LLM agents from effectively and efficiently mitigating error propagation and learning from environmental feedback (Qiao et al., 2023; Shinn et al., 2023; Yang et al., 2023 In such cases, it is generally preferable to…”
BackgroundToolformer: Language Models Can Teach Themselves to Use Tools
Schick, T., Dwivedi-Yu, J., Dessì, R., Raileanu, R., Lomeli, M., Zettlemoyer, L., Cancedda, N., & Scialom, T. (2023) · arXiv · doi:10.48550/arxiv.2302.04761 · Cited by 1,150 · cited 3× · see citing works
“We will explore stricter evaluation metrics to assess the cases of misinformation that could pose a risk within clinical settings in our future work.”
BackgroundMethodReflexion: Language Agents with Verbal Reinforcement Learning
Shinn, N., Cassano, F., Berman, E., Gopinath, A., Narasimhan, K., & Yao, S. (2023) · arXiv · doi:10.48550/arxiv.2303.11366 · Cited by 1,087 · cited 1× · see citing works
“We will explore stricter evaluation metrics to assess the cases of misinformation that could pose a risk within clinical settings in our future work.”
MethodAutonomous chemical research with large language models
Boiko, D. A., MacKnight, R., Kline, B., & Gomes, G. (2023) · Nature · doi:10.1038/s41586-023-06792-0 · Cited by 1,050 · cited 1× · see citing works
“We will explore stricter evaluation metrics to assess the cases of misinformation that could pose a risk within clinical settings in our future work.”
MethodYu, T., Zhang, R., Yang, K., Yasunaga, M., Wang, D., Li, Z., Ma, J., Li, I., Yao, Q., Roman, S., et al. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1425 · Cited by 1,034 · cited 3× · see citing works
“The SPIDER (Yu et al., 2018) dataset, which is commonly used in SQL base-lines (Pourreza and Rafiei, 2023), typically only involves referencing information from an average of 1.1 tables per question .”
BackgroundMethodInfluentialThe Rise and Potential of Large Language Model Based Agents: A Survey
Xi, Z., Chen, W., Guo, X., He, W., Ding, Y., Hong, B., Zhang, M., Wang, J., Jin, S., Zhou, E., et al. (2023) · arXiv · doi:10.48550/arxiv.2309.07864 · Cited by 972 · cited 1× · see citing works
“We will explore stricter evaluation metrics to assess the cases of misinformation that could pose a risk within clinical settings in our future work.”
MethodA large language model for electronic health records
Yang, X., Chen, A., PourNejatian, N., Shin, H. C., Smith, K. E., Parisien, C., Compas, C., Martin, C., Costa, A. B., Flores, M. G., et al. (2022) · npj Digital Medicine · doi:10.1038/s41746-022-00742-2 · Cited by 847 · cited 1× · see citing works
“Large language models (LLMs) (OpenAI, 2023; Anil et al., 2023) bring us one step closer to autonomous agents with extensive knowledge and substantial instruction-following abilities from di-a et al., 2017) and SPIDER (Yu et al., 2018), multi-tabular reasoning tasks within EHRs (orange) typically…”
BackgroundSelf-Consistency Improves Chain of Thought Reasoning in Language Models
Wang, X., Wei, J., Schuurmans, D., Le, Q., Chi, E., Narang, S., Chowdhery, A., & Zhou, D. (2022) · arXiv · doi:10.48550/arxiv.2203.11171 · Cited by 829 · cited 1× · see citing works
“Alternatively, an autonomous agent could facilitate clinicians to communicate with EHRs in nat-ural languages, translating clinical questions into machine-interpretable queries, planning a sequence of actions, and ultimately delivering the final responses.”
BackgroundSMART on FHIR: a standards-based, interoperable apps platform for electronic health records
Mandel, J. C., Kreda, D. A., Mandl, K. D., Kohane, I. S., & Ramoni, R. B. (2016) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocv189 · Cited by 829 · cited 1× · see citing works
“…when dealing with EHRs in existing clinical settings ( left ). sistance from data engineers for clinicians to obtain information beyond these rules (Mandel et al., 2016; Bender and Sartipi, 2013), leading to inef-ficiencies and delays that may impact the quality and timeliness of patient care.”
BackgroundAugmenting large language models with chemistry tools
M. Bran, A., Cox, S., Schilter, O., Baldassari, C., White, A. D., & Schwaller, P. (2024) · Nature Machine Intelligence · doi:10.1038/s42256-024-00832-8 · Cited by 794 · cited 1× · see citing works
“We will explore stricter evaluation metrics to assess the cases of misinformation that could pose a risk within clinical settings in our future work.”
MethodCode as Policies: Language Model Programs for Embodied Control
Liang, J., Huang, W., Xia, F., Xu, P., Hausman, K., Ichter, B., Florence, P., & Zeng, A. (2023) · 2023 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra48891.2023.10160591 · Cited by 767 · cited 1× · see citing works
“To mitigate ambiguities and misinterpretations in plan generation, an increasing number of LLM agents (Gao et al., 2023; Liang et al., 2023; Sun et al., 2023; Chen et al., 2023; Zhuang et al., 2024) employ code prompts as planner interface instead of natu-ral language prompts.”
BackgroundSeq2SQL: Generating Structured Queries from Natural Language using Reinforcement LearningPreprint
Zhong, V., Xiong, C., & Socher, R. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1709.00103 · Cited by 733 · cited 1× · see citing works
“…al., 2023) bring us one step closer to autonomous agents with extensive knowledge and substantial instruction-following abilities from di-a et al., 2017) and SPIDER (Yu et al., 2018), multi-tabular reasoning tasks within EHRs (orange) typically involve a significantly larger number of records per…”
BackgroundInfluentialJin, D., Pan, E., Oufattole, N., Weng, W.-H., Fang, H., & Szolovits, P. (2021) · doi:10.20944/preprints202105.0498.v1 · Cited by 718 · cited 1× · see citing works
“One particularly notable capability of LLM agents is tool-usage (Schick et al., 2023; Qin et al., 2023), where they can utilize external tools ( e.g. , calculators, APIs, etc. ), interact with environments, and generate action plans with intermediate reasoning steps that can be executed…”
BackgroundElectronic health records to facilitate clinical research
Cowie, M. R., Blomster, J. I., Curtis, L. H., Duclaux, S., Ford, I., Fritz, F., Goldman, S., Janmohamed, S., Kreuzer, J., Leenay, M., et al. (2017) · Clinical Research in Cardiology · doi:10.1007/s00392-016-1025-6 · Cited by 651 · cited 1× · see citing works
“In clinical research and practice, clinicians actively interact with EHR systems to access and retrieve patient data, ranging from detailed individual-level records to comprehensive population-level insights (Cowie et al., 2017).”
BackgroundReAct: Synergizing Reasoning and Acting in Language Models
Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., & Cao, Y. (2022) · arXiv · doi:10.48550/arxiv.2210.03629 · Cited by 608 · cited 2× · see citing works
“Alternatively, an autonomous agent could facilitate clinicians to communicate with EHRs in nat-ural languages, translating clinical questions into machine-interpretable queries, planning a sequence of actions, and ultimately delivering the final responses.”
BackgroundMethodMedAgents: Large Language Models as Collaborators for Zero-shot Medical ReasoningPreprint
Tang, X., Zou, A.-N., Zhang, Z., Li, Z.-M., Zhao, Y., Zhang, X., Cohan, A., & Gerstein, M. (2023) · Annual Meeting of the Association for Computational Linguistics · doi:10.48550/arxiv.2311.10537 · Cited by 571 · see citing works
HL7 FHIR: An Agile and RESTful approach to healthcare information exchange
Bender, D., & Sartipi, K. (2013) · Proceedings of the 26th IEEE International Symposium on Computer-Based Medical Systems · doi:10.1109/cbms.2013.6627810 · Cited by 540 · cited 1× · see citing works
“…when dealing with EHRs in existing clinical settings ( left ). sistance from data engineers for clinicians to obtain information beyond these rules (Mandel et al., 2016; Bender and Sartipi, 2013), leading to inef-ficiencies and delays that may impact the quality and timeliness of patient care.”
BackgroundChameleon: Plug-and-Play Compositional Reasoning with Large Language ModelsPreprint
Lu, P., Peng, B., Cheng, H., Galley, M., Chang, K.-W., Wu, Y., Zhu, S.-C., & Gao, J.-F. (2023) · Neural Information Processing Systems · doi:10.48550/arxiv.2304.09842 · Cited by 534 · see citing works
HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face
Shen, Y., Song, K., Tan, X., Li, D., Lu, W., & Zhuang, Y. (2023) · arXiv · doi:10.48550/arxiv.2303.17580 · Cited by 477 · cited 2× · see citing works
“…and efficiently mitigating error propagation and learning from environmental feedback (Qiao et al., 2023; Shinn et al., 2023; Yang et al., 2023 In such cases, it is generally preferable to acknowledge failure rather than generate an incorrect answer, as this could lead to an inaccurate diagnosis.”
BackgroundSelf-citationHealth system-scale language models are all-purpose prediction engines
Jiang, L. Y., Liu, X. C., Nejatian, N. P., Nasir-Moin, M., Wang, D., Abidin, A., Eaton, K., Riina, H. A., Laufer, I., Punjabi, P., et al. (2023) · Nature · doi:10.1038/s41586-023-06160-y · Cited by 460 · cited 2× · see citing works
“Alternatively, an autonomous agent could facilitate clinicians to communicate with EHRs in nat-ural languages, translating clinical questions into machine-interpretable queries, planning a sequence of actions, and ultimately delivering the final responses.”
BackgroundGunter, T. D., & Terry, N. P. (2005) · Journal of Medical Internet Research · doi:10.2196/jmir.7.1.e3 · Cited by 440 · cited 1× · see citing works
“An electronic health record (EHR) is a digital version of a patient’s medical history maintained by healthcare providers over time (Gunter and Terry, 2005).”
BackgroundEmpowering Biomedical Discovery with AI AgentsPreprint
Gao, S., Fang, A., Huang, Y.-P., Giunchiglia, V., Noori, A., Schwarz, J., Ektefaie, Y., Kondic, J., & Zitnik, M. (2024) · Cell · doi:10.48550/arxiv.2404.02831 · Cited by 424 · see citing works
ToolQA: A Dataset for LLM Question Answering with External ToolsPreprint
Zhuang, Y.-C., Yu, Y., Wang, K., et al. (2023) · Neural Information Processing Systems · doi:10.48550/arxiv.2306.13304 · Cited by 421 · cited 1× · see citing works
“Compared to existing EHR management that relies heavily on human effort, the adoption of autonomous agents holds great potential to efficiently simplify workflows and reduce workloads for clinicians (Figure 1).”
BackgroundSelf-citationLeast-to-Most Prompting Enables Complex Reasoning in Large Language Models
Zhou, D., Schärli, N., Hou, L., Wei, J., Scales, N., Wang, X., Schuurmans, D., Cui, C., Bousquet, O., Le, Q., et al. (2022) · arXiv · doi:10.48550/arxiv.2205.10625 · Cited by 380 · see citing works
Empowering biomedical discovery with AI agents
Gao, S., Fang, A., Huang, Y., Giunchiglia, V., Noori, A., Schwarz, J. R., Ektefaie, Y., Kondic, J., & Zitnik, M. (2024) · Cell · doi:10.1016/j.cell.2024.09.022 · Cited by 315 · see citing works
Camel: Communicative agents for" mind" exploration of large language model society
Li, G., Hammoud, H., Itani, H., Khizbullin, D., & Ghanem, B. (2023) · Advances in Neural Information Processing Systems 36 · doi:10.52202/075280-2264 · Cited by 314 · cited 1× · see citing works
“We will explore stricter evaluation metrics to assess the cases of misinformation that could pose a risk within clinical settings in our future work.”
MethodLanguage Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents
Huang, W., Abbeel, P., Pathak, D., & Mordatch, I. (2022) · arXiv · doi:10.48550/arxiv.2201.07207 · Cited by 304 · cited 1× · see citing works
“…and efficiently mitigating error propagation and learning from environmental feedback (Qiao et al., 2023; Shinn et al., 2023; Yang et al., 2023 In such cases, it is generally preferable to acknowledge failure rather than generate an incorrect answer, as this could lead to an inaccurate diagnosis.”
BackgroundLi, J., Hui, B., Qu, G., Yang, J., Li, B., Li, B., Wang, B., Qin, B., Cao, R., Geng, R., et al. (2023) · arXiv · doi:10.48550/arxiv.2305.03111 · Cited by 278
WebGPT: Browser-assisted question-answering with human feedback
Nakano, R., Hilton, J., Balaji, S., Wu, J., Ouyang, L., Kim, C., Hesse, C., Jain, S., Kosaraju, V., Saunders, W., et al. (2021) · arXiv · doi:10.48550/arxiv.2112.09332 · Cited by 272 · cited 1× · see citing works
“We will explore stricter evaluation metrics to assess the cases of misinformation that could pose a risk within clinical settings in our future work.”
MethodDIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction
Pourreza, M., & Rafiei, D. (2023) · arXiv · doi:10.48550/arxiv.2304.11015 · Cited by 248 · cited 6×
“DIN-SQL (Pourreza and Rafiei, 2023) establishes a set of rules to automatically self-correct the SQL commands generated.”
BackgroundMethodInfluentialGorilla: Large Language Model Connected with Massive APIs
Patil, S., Zhang, T., Wang, X., & Gonzalez, J. (2024) · Advances in Neural Information Processing Systems 37 · doi:10.52202/079017-4020 · Cited by 226 · cited 1× · see citing works
“We will explore stricter evaluation metrics to assess the cases of misinformation that could pose a risk within clinical settings in our future work.”
MethodAutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
Wu, Q., Bansal, G., Zhang, J., Wu, Y., Li, B., Zhu, E., Jiang, L., Zhang, X., Zhang, S., Liu, J., et al. (2023) · arXiv · doi:10.48550/arxiv.2308.08155 · Cited by 193 · cited 8× · see citing works
“(5) Self-Debugging and AutoGen present a notable performance gain over other baselines, as they leverage code interfaces and consider the errors from the coding environment, leading to a large improvement in the completion rate.”
BackgroundMethodResultInfluentialSelf-citation(2024) · doi:10.1145/3704435 · Cited by 184 · cited 1× · see citing works
“One particularly notable capability of LLM agents is tool-usage (Schick et al., 2023; Qin et al., 2023), where they can utilize external tools ( e.g. , calculators, APIs, etc. ), interact with environments, and generate action plans with intermediate reasoning steps that can be executed…”
BackgroundSelf-citationExpeL: LLM Agents Are Experiential Learners
Zhao, A., Huang, D., Xu, Q., Lin, M., Liu, Y.-J., & Huang, G. (2023) · arXiv · doi:10.48550/arxiv.2308.10144 · Cited by 179 · see citing works
Jin, Q., Yang, Y., Chen, Q., & Lu, Z. (2024) · Bioinformatics · doi:10.1093/bioinformatics/btae075 · Cited by 176 · see citing works
Reasoning with Language Model is Planning with World Model
Hao, S., Gu, Y., Ma, H., Hong, J. J., Wang, Z., Wang, D. Z., & Hu, Z. (2023) · arXiv · doi:10.48550/arxiv.2305.14992 · Cited by 166 · cited 1× · see citing works
“Alternatively, an autonomous agent could facilitate clinicians to communicate with EHRs in nat-ural languages, translating clinical questions into machine-interpretable queries, planning a sequence of actions, and ultimately delivering the final responses.”
BackgroundPAL: Program-aided Language Models
Gao, L., Madaan, A., Zhou, S., Alon, U., Liu, P., Yang, Y., Callan, J., & Neubig, G. (2022) · arXiv · doi:10.48550/arxiv.2211.10435 · Cited by 155 · cited 4× · see citing works
“Alternatively, an autonomous agent could facilitate clinicians to communicate with EHRs in nat-ural languages, translating clinical questions into machine-interpretable queries, planning a sequence of actions, and ultimately delivering the final responses.”
BackgroundMethodInfluentialConversational Health Agents: A Personalized LLM-Powered Agent FrameworkPreprint
Abbasian, M., Azimi, I., Rahmani, A. M., et al. (2023) · arXiv.org · doi:10.48550/arxiv.2310.02374 · Cited by 150 · cited 1× · see citing works
“We will explore stricter evaluation metrics to assess the cases of misinformation that could pose a risk within clinical settings in our future work.”
MethodToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search
Zhuang, Y.-C., Chen, X., Yu, T., et al. (2023) · arXiv.org · doi:10.48550/arxiv.2310.13227 · Cited by 142 · cited 3×
“We will explore stricter evaluation metrics to assess the cases of misinformation that could pose a risk within clinical settings in our future work.”
BackgroundMethodSelf-citationChen, W., Ma, X., Wang, X., & Cohen, W. W. (2022) · arXiv · doi:10.48550/arxiv.2211.12588 · Cited by 125 · cited 2× · see citing works
“…maintain a thorough metadata I of all the reference EHRs, including overall data descriptions D and the detailed column descriptions To further extract additional background knowledge essential for addressing the complex query q , we then distill key information from the detailed introduction I .”
BackgroundMethodAPI-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs
Li, M., Zhao, Y., Yu, B., Song, F., Li, H., Yu, H., Li, Z., Huang, F., & Li, Y. (2023) · Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2023.emnlp-main.187 · Cited by 124 · see citing works
ChatGPT, Bard, and large language models for biomedical research: opportunities and pitfalls
Thapa, S., & Adhikari, S. (2023) · Annals of Biomedical Engineering · doi:10.1007/s10439-023-03284-0 · Cited by 111 · cited 1× · see citing works
“…multi-tabular reasoning tasks within EHRs (orange) typically involve a significantly larger number of records per table and necessitate querying multiple tables to answer each question, thereby requiring more advanced reasoning and problem-solving capabilities. verse corpora during pretraining.”
BackgroundText-to-SQL Generation for Question Answering on Electronic Medical Records
Wang, P., Shi, T., & Reddy, C. K. A. (2020) · International World Wide Web Conference (WWW) · doi:10.1145/3366423.3380120 · Cited by 96 · cited 3× · see citing works
“In contrast to traditional supervised settings (Lee et al., 2022; Wang et al., 2020) that require over 10K training samples with manually crafted annotations, EHRAgent demonstrates its efficiency by necessitating only four demonstrations.”
BackgroundMaking Language Models Better Tool Learners with Execution FeedbackPreprint
Qiao, S.-F., Gui, H., Lv, C.-F., Jia, Q.-H., Chen, H.-J., & Zhang, N. (2023) · North American Chapter of the Association for Computational Linguistics · doi:10.48550/arxiv.2305.13068 · Cited by 93 · cited 1× · see citing works
“…and execution, however, prevents LLM agents from effectively and efficiently mitigating error propagation and learning from environmental feedback (Qiao et al., 2023; Shinn et al., 2023; Yang et al., 2023 In such cases, it is generally preferable to acknowledge failure rather than generate an…”
BackgroundEHRSQL: A Practical Text-to-SQL Benchmark for Electronic Health Records
Lee, G., Hwang, H., Bae, S., et al. (2023) · Neural Information Processing Systems · doi:10.48550/arxiv.2301.07695 · Cited by 78 · cited 4×
“Firstly, to overcome the lack of domain knowledge in LLMs, we instruct EHRAgent to integrate query-specific medical information for effectively reasoning from the given query and locating the query-related tables or records.”
BackgroundMethodInfluentialTeaching Large Language Models to Self-Debug
Chen, X., Lin, M., Schärli, N., & Zhou, D. (2023) · arXiv · doi:10.48550/arxiv.2304.05128 · Cited by 77 · see citing works
Augmenting Language Models with Long-Term Memory
Wang, W., Dong, L., Cheng, H., Liu, X., Yan, X., Gao, J., & Wei, F. (2023) · arXiv · doi:10.48550/arxiv.2306.07174 · Cited by 72 · cited 2× · see citing works
“We will explore stricter evaluation metrics to assess the cases of misinformation that could pose a risk within clinical settings in our future work.”
BackgroundMethodQin, Y., Liang, S., Ye, Y., Zhu, K., Yan, L., Lu, Y., Lin, Y., Cong, X., Tang, X., Qian, B., et al. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2307.16789 · Cited by 71 · cited 1× · see citing works
“The disconnection between plan generation and execution, however, prevents LLM agents from effectively and efficiently mitigating error propagation and learning from environmental feedback (Qiao et al., 2023; Shinn et al., 2023; Yang et al., 2023 In such cases, it is generally preferable to…”
BackgroundConversational health agents: a personalized large language model-powered agent framework
Abbasian, M., Azimi, I., Rahmani, A. M., & Jain, R. (2025) · JAMIA Open · doi:10.1093/jamiaopen/ooaf067 · Cited by 52 · see citing works
Shi, W., Zhuang, Y., Zhu, Y., Iwinski, H., Wattenbarger, M., & Wang, M. D. (2023) · Proceedings of the 14th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics · doi:10.1145/3584371.3612956 · Cited by 47 · cited 1× · see citing works
“…models (LLMs) (OpenAI, 2023; Anil et al., 2023) bring us one step closer to autonomous agents with extensive knowledge and substantial instruction-following abilities from di-a et al., 2017) and SPIDER (Yu et al., 2018), multi-tabular reasoning tasks within EHRs (orange) typically involve a…”
BackgroundSelf-citationTALM: Tool Augmented Language Models
Parisi, A., Zhao, Y., & Fiedel, N. (2022) · arXiv · doi:10.48550/arxiv.2205.12255 · Cited by 35 · cited 1× · see citing works
“The disconnection between plan generation and execution, however, prevents LLM agents from effectively and efficiently mitigating error propagation and learning from environmental feedback (Qiao et al., 2023; Shinn et al., 2023; Yang et al., 2023 In such cases, it is generally preferable to…”
BackgroundAdaPlanner: Adaptive Planning from Feedback with Language Models
Sun, H., Zhuang, Y., Kong, L., Dai, B., & Zhang, C. (2023) · arXiv · doi:10.48550/arxiv.2305.16653 · Cited by 31 · cited 3×
“Alternatively, an autonomous agent could facilitate clinicians to communicate with EHRs in nat-ural languages, translating clinical questions into machine-interpretable queries, planning a sequence of actions, and ultimately delivering the final responses.”
BackgroundMethodSelf-citationPOLYIE: A Dataset of Information Extraction from Polymer Material Scientific Literature
Cheung, J. J., Zhuang, Y.-C., Li, Y., et al. (2023) · North American Chapter of the Association for Computational Linguistics · doi:10.48550/arxiv.2311.07715 · Cited by 29
Self-citationInterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback
Yang, J., Prabhakar, A., Narasimhan, K., & Yao, S. (2023) · arXiv · doi:10.48550/arxiv.2306.14898 · Cited by 26 · cited 2×
“…maintain a thorough metadata I of all the reference EHRs, including overall data descriptions D and the detailed column descriptions To further extract additional background knowledge essential for addressing the complex query q , we then distill key information from the detailed introduction I .”
BackgroundMethodExecutable Code Actions Elicit Better LLM Agents
Wang, X., Chen, Y., Yuan, L., Zhang, Y., Li, Y., Peng, H., & Ji, H. (2024) · arXiv · doi:10.48550/arxiv.2402.01030 · Cited by 23 · cited 1× · see citing works
“…and efficiently mitigating error propagation and learning from environmental feedback (Qiao et al., 2023; Shinn et al., 2023; Yang et al., 2023 In such cases, it is generally preferable to acknowledge failure rather than generate an incorrect answer, as this could lead to an inaccurate diagnosis.”
BackgroundOn Evaluating the Integration of Reasoning and Action in LLM Agents with Database Question Answering
Nan, L., Zhang, E., Zou, W., et al. (2023) · NAACL-HLT · doi:10.48550/arxiv.2311.09721 · Cited by 21 · cited 1×
“We will explore stricter evaluation metrics to assess the cases of misinformation that could pose a risk within clinical settings in our future work.”
MethodemrKBQA: A Clinical Knowledge-Base Question Answering Dataset
Raghavan, P., Liang, J. J., Mahajan, D., Chandra, R., & Peter Szolovits, B. (2021) · Workshop on Biomedical Language Processing (BioNLP) · doi:10.18653/v1/2021.bionlp-1.7 · Cited by 20 · cited 1× · see citing works
“Compared to supervised learning like text-to-SQL (Wang et al., 2020; Raghavan et al., 2021; Lee et al., 2022) that requires extensive training on over 10K samples with detailed annotations ( e.g. , manually generated corresponding code for each query), LLM agents enable complex tabular reasoning…”
BackgroundMINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback
Wang, X., Wang, Z., Liu, J., Chen, Y., Yuan, L., Peng, H., & Ji, H. (2023) · arXiv · doi:10.48550/arxiv.2309.10691 · Cited by 18 · cited 1× · see citing works
“LLMs have rapidly evolved from text generators into core computational engines of autonomous agents, with advanced planning and tool-use capabilities (Schick et al., 2023; Shen et al., 2023; Wang et al., 2024b; Yuan et al., 2024a,b; Zhuang et al., 2023).”
BackgroundCRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets
Yuan, L., Chen, Y., Wang, X., Fung, Y. R., Peng, H., & Ji, H. (2023) · arXiv · doi:10.48550/arxiv.2309.17428 · Cited by 11 · cited 1× · see citing works
“LLMs have rapidly evolved from text generators into core computational engines of autonomous agents, with advanced planning and tool-use capabilities (Schick et al., 2023; Shen et al., 2023; Wang et al., 2024b; Yuan et al., 2024a,b; Zhuang et al., 2023).”
BackgroundEcoAssistant: Using LLM Assistant More Affordably and Accurately
Zhang, J., Krishna, R., Awadallah, A. H., & Wang, C. (2023) · arXiv · doi:10.48550/arxiv.2310.03046 · Cited by 8 · cited 1× · see citing works
“…et al., 2023; Qin et al., 2023), where they can utilize external tools ( e.g. , calculators, APIs, etc. ), interact with environments, and generate action plans with intermediate reasoning steps that can be executed sequentially towards a valid solution (Wu et al., 2023; Zhang et al., 2023).”
BackgroundSelf-citationEASYTOOL: Enhancing LLM-based Agents with Concise Tool Instruction
Yuan, S., Song, K., Chen, J., Tan, X., Shen, Y., Kan, R., Li, D., & Yang, D. (2024) · arXiv · doi:10.48550/arxiv.2401.06201 · Cited by 4 · see citing works
MindAgent: Emergent Gaming Interaction
Gong, R., Huang, Q., Ma, X., Vo, H., Durante, Z., Noda, Y., Zheng, Z., Zhu, S.-C., Terzopoulos, D., Fei-Fei, L., et al. (2023) · arXiv · doi:10.48550/arxiv.2309.09971 · Cited by 1 · see citing works
Flagged first, then by citations
Research works printed but not linked: 4
- Bae Seongsu, Kyung Daeun, Ryu Jaehee, Cho Eunbyeol, Lee Gyubok, Kweon Sunjun, Oh Jungwoo, Ji Lei, Eric I-Chao Chang Tackeun Kim, and Choi Edward. 2023. EHRXQA: A multi-modal question answering dataset for electronic health records with chest x-ray images. In Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track.
- Kirk James R, Wray Robert E, Lindes Peter, and Laird John E. 2024. Improving knowledge extraction from llms for task learning through agent analysis. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, pages 18390– 18398.
- OpenAI. 2023. Gpt-4 technical report. arXiv.
- Qin Yujia, Liang Shihao, Ye Yining, Zhu Kunlun, Yan Lan, Lu Yaxi, Lin Yankai, Cong Xin, Tang Xiangru, Qian Bill, Zhao Sihan, Hong Lauren, Tian Runchu, Xie Ruobing, Zhou Jie, Gerstein Mark, dahai li, Zhiyuan Liu, and Sun Maosong. 2024. ToolLLM: Facilitating large language models to master 16000+ real-world APIs. In The Twelfth International Conference on Learning Representations.
Cited by
Sorted by citations
A Survey on the Memory Mechanism of Large Language Model-based Agents
Zhang, Z., Dai, Q., Bo, X., Ma, C., Li, R., Chen, X., Zhu, J., Dong, Z., & Wen, J.-R. (2025) · ACM Transactions on Information Systems · doi:10.1145/3748302 · Cited by 118 · see citing works
MedAgentBench: a virtual EHR environment to benchmark medical LLM agents
Jiang, Y., Black, K. C., Geng, G., Park, D., Zou, J., Ng, A. Y., & Chen, J. H. (2025) · NEJM AI · doi:10.1056/aidbp2500144 · Cited by 66 · see citing works
Systematic review: The use of large language models as medical chatbots in digestive diseases
Giuffrè, M., Kresevic, S., You, K., Dupont, J., Huebner, J., Grimshaw, A. A., & Shung, D. L. (2024) · Alimentary Pharmacology & Therapeutics · doi:10.1111/apt.18058 · Cited by 59 · see citing works
LLM-Based Agents for Tool Learning: A Survey
Xu, W., Huang, C., Gao, S., & Shang, S. (2025) · Data Science and Engineering · doi:10.1007/s41019-025-00296-9 · Cited by 69 · see citing works
SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
Yang, J., Jimenez, C. E., Wettig, A., Lieret, K., Yao, S., Narasimhan, K., & Press, O. (2024) · arXiv · doi:10.48550/arxiv.2405.15793 · Cited by 31 · see citing works
A survey of table reasoning with large language models
Zhang, X., Wang, D., Dou, L., Zhu, Q., & Che, W. (2025) · Frontiers of Computer Science · doi:10.1007/s11704-024-40330-z · Cited by 35 · see citing works
Critique of impure reason: Unveiling the reasoning behaviour of medical large language models
Sim, S. Z. Y., & Chen, T. (2025) · eLife · doi:10.7554/elife.106187 · Cited by 24 · see citing works
AI agent in healthcare: applications, evaluations, and future directions
Zhao, L., Liu, S., Xin, T., Tan, J., Wang, X., Li, Y., Bian, Z., Chen, Y., Kong, F., Bian, J., et al. (2026) · npj Artificial Intelligence · doi:10.1038/s44387-026-00076-4 · Cited by 26 · see citing works
Unveiling Privacy Risks in LLM Agent Memory
Wang, B., He, W., Zeng, S., Xiang, Z., Xing, Y., Tang, J., & He, P. (2025) · Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2025.acl-long.1227 · Cited by 24 · see citing works
ArgMed-Agents: Explainable Clinical Decision Reasoning with LLM Disscusion via Argumentation Schemes
Hong, S., Xiao, L., Zhang, X., & Chen, J. (2024) · 2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm62325.2024.10822109 · Cited by 21 · see citing works
“These methods use LLMs as computational engines for autonomous agents, and optimise the reasoning, planning capabilities of LLMs through external tools (e.g. symbolic solvers, APIs, retrieval tools, etc.) [20], [21], multi-agent interactions [22] and novel algorithmic frameworks [23].”
Xu, X., & Sankar, R. (2025) · Information · doi:10.3390/info16100894 · Cited by 20 · see citing works
“…biomedical agents employ tool calling in tasks such as literature and gene retrieval via PubMed or NCBI APIs [4,26], chemical structure analysis via cheminformatics packages [20], and automated experimentation through lab interface protocols, or interaction with structured EHR databases [49].”
Younesi, A., Oustad, E., Ansari, M., Fahringer, T., & Buyya, R. (2025) · Internet of Things · doi:10.1016/j.iot.2025.101815 · Cited by 23 · see citing works
Vatsal, S., Dubey, H., & Singh, A. (2026) · IEEE Access · doi:10.1109/access.2026.3651218 · Cited by 21 · see citing works
“They can reason over multi-table EHRs to answer record level queries as shown by EHRAgent [126].”
Transforming wearable data into personal health insights using large language model agents
Merrill, M. A., Paruchuri, A., Rezaei, N., Kovacs, G., Perez, J., Liu, Y., Schenck, E., Hammerquist, N., Sunshine, J., Tailor, S. A., et al. (2026) · Nature Communications · doi:10.1038/s41467-025-67922-y · Cited by 53 · see citing works
“While agents have shown effectiveness for exploring objec-tive tabular data in domains like electronic medical records 23,39 – 44 , they have not yet been adapted to handle the complex, open-ended, and personalized nature of wearable health queries, which often require substantial domain knowledge…”
Yang, T., Xiao, Y., Bao, Z., Hao, J., & Peng, J. (2025) · Briefings in Bioinformatics · doi:10.1093/bib/bbaf601 · Cited by 23 · see citing works
Altermatt, F. R., Neyem, A., Sumonte, N. I., Mendoza, M., Villagrán, I., & Lacassie, H. J. (2025) · BMC Medical Education · doi:10.1186/s12909-025-07250-3 · Cited by 15 · see citing works
AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents
Wang, H., Poskitt, C. M., & Sun, J. (2026) · Proceedings of the 2026 IEEE/ACM 48th International Conference on Software Engineering · doi:10.1145/3744916.3764546 · Cited by 14 · see citing works
A Survey on Unifying Large Language Models and Knowledge Graphs for Biomedicine and Healthcare
Xu, R., Jiang, P., Luo, L., Xiao, C., Cross, A., Pan, S., Sun, J., & Yang, C. (2025) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3711896.3736556 · Cited by 16 · see citing works
Self-citationUnstructured Electronic Health Records of Dysphagic Patients Analyzed by Large Language Models
Neubig, L., Larsen, D., Kunduk, M., & Kist, A. M. (2025) · IEEE Journal of Translational Engineering in Health and Medicine · doi:10.1109/jtehm.2025.3571255 · Cited by 11 · see citing works
“Shi et al. additionally propose the EHR-Agent, which enriches the learning and guiding approach of LLMs by including a long-term memory to learn from the past [33].”
AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases
Chen, Z., Xiang, Z., Xiao, C., Song, D., & Li, B. (2024) · arXiv · doi:10.48550/arxiv.2407.12784 · Cited by 10 · see citing works
“LLM Agent : To demonstrate the generalization of A GENT P OISON , we select three types of real-world agents across a variety of tasks: Agent-Driver [22] for autonomous driving, ReAct [36] agent for knowledge-intensive QA, and EHRAgent [25] for healthcare record management.”
InfluentialA scalable framework for evaluating health language models
Mallinar, N., Heydari, A. A., Liu, X., Faranesh, A. Z., Winslow, B. D., Hammerquist, N., Graef, B., Speed, C., Malhotra, M., Patel, S., et al. (2026) · npj Digital Medicine · doi:10.1038/s41746-026-02492-x · Cited by 14 · see citing works
“…tools, but represent a potential paradigm shift in how medical knowledge and information is accessed, synthesized, and utilized, with applications such as medical question and answering 2 , differential diagnosis 3 , electronic health record reasoning 4 , and biomedical research discovery 5 .”
A survey of foundation models for IoT: taxonomy and criteria-based analysis
Wei, H., Lee, D. Y., Rohal, S., Hu, Z., Rossi, R. A., Fang, S., & Pan, S. (2025) · CCF Transactions on Pervasive Computing and Interaction · doi:10.1007/s42486-025-00208-w · Cited by 8 · see citing works
Deep multimodal learning for time series analysis in social computing: a survey
Yang, C., Chen, Y., Li, Z., Wang, X., Shi, K., Yao, L., Xu, G., & Guo, Z. (2025) · International Journal of Multimedia Information Retrieval · doi:10.1007/s13735-025-00363-x · Cited by 4 · see citing works
Self-citationLu, J., Brown, S., Liu, S., Zhao, S., Dong, K., Bold, D., Fundora, M. P., Aljiffry, A., Fedorov, A., Grunwell, J. R., et al. (2025) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc58623.2025.11251673 · Cited by 4 · see citing works
“Pre-trained on massive textual corpus that covers public EHR databases, transformer-based models have shown promising in adults-centered risk prediction tasks [22], [23], [24].”
An Agent-Based Adaptive Medical Dialogue Service for Personalized Healthcare
Xu, F., Cheng, P., Gao, F., Jin, Y., Yan, S., Huang, Q. Y., Wang, Y., Ren, X., & Gu, J. (2025) · International Journal of Web Services Research · doi:10.4018/ijwsr.371758 · Cited by 3 · see citing works
“Shi et al. (2024) developed a medical agent named Electronic Health Record Agent (EHRAgent), which integrated medical knowledge, LLMs, and external tools to address the challenge of few-shot reasoning in electronic health records.”
Progent: Securing AI Agents with Privilege Control
Shi, T., He, J., Wang, Z., Li, H., Wu, L., Guo, W., & Song, D. (2025) · arXiv · doi:10.48550/arxiv.2504.11703 · Cited by 3 · see citing works
MoMA: a mixture-of-multimodal-agents architecture for enhancing clinical prediction modelling
Gao, J., Rahman, M., Caskey, J., Oguss, M., O’Rourke, A., Brown, R., Stey, A., Mayampurath, A., Churpek, M. M., Chen, G., et al. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-02219-4 · Cited by 2 · see citing works
“For example, multimodal LLMs such as LLaVA-Med 23 and CXR-LLAVA 34 can generate text summaries from medical images, while structured EHR data can be summarized using general-purpose LLMs 78 like Llama-3 79 .”
Cai, Q., Yang, L., Xiao, J., Ma, J., Liu, M., & Pan, X. (2025) · Diagnostics · doi:10.3390/diagnostics15141829 · Cited by 2 · see citing works
“LLMs, with powerful abilities in semantic understanding, knowledge representation, and logical reasoning, have advantages in error detection and correction in EMRs [9,10].”
Wang, S., & Ye, Q. (2025) · JMIR Medical Informatics · doi:10.2196/73857 · Cited by 2 · see citing works
“Agents have been proven to possess capabilities beyond those of LLMs [21-23].”
Co-Data: Cultivating Effective Human-LLM Collaboration for Collaborative Data Processing
Pachera, A., Mauri, A., Imteyaz, K., Yang, J., Umuhoza, E., Bonifati, A., Lahav, M., & Goyal, N. (2026) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3772363.3778724 · Cited by 2 · see citing works
MEDS — An Emerging Data Standard and Ecosystem for Health AI Research
McDermott, M. B. A., Steinberg, E., Fries, J., van de Water, R. P., Pang, C., Rockenschaub, P., Renc, P., Oh, J. H., Stankevičiūtė, K., Xu, J., et al. (2026) · NEJM AI · doi:10.1056/aira2501253 · Cited by 3 · see citing works
Tutorial: guidance on the use of large language models for medical research
Jin, Q., Wan, N., Leaman, R., Tian, S., Wang, Z., Yang, Y., Wang, Z., Xiong, G., Lai, P.-T., Zhu, Q. L., et al. (2026) · Nature Protocols · doi:10.1038/s41596-026-01408-z · Cited by 9 · see citing works
Incorporating Medical Assistants in eHealth Environments Using an Agentic RAG Approach
Kalathas, D., Menychtas, A., Maglogiannis, I. G., & Tsanakas, P. D. (2025) · IFIP advances in information and communication technology · doi:10.1007/978-3-031-96235-6_12 · Cited by 2 · see citing works
Transfer Learning of Tabular Data by Finetuning Large Language Models
Rabbani, S. B., Kowsar, I., & Samad, M. D. (2024) · International Conference on Electrical and Computer Engineering (ICECE) · doi:10.1109/icece64886.2024.11024938 · Cited by 2 · see citing works
“Recent studies show promising performance of LLMs in zero or few shot learning of tabular data on tasks like classification [8, 9, 10], reasoning [11, 12], and text generation [11, 13].”
EXR: An Interactive Immersive EHR Visualization in Extended Reality
Marteau, B. L., Tan, S. Q. Y., Li, J., Hornback, A. M., Zhong, Y., Wang, S., Lowson, C., Woloff, J., Pahys, J. M., Hwang, S. W., et al. (2025) · IEEE International Conference on Intelligent Reality (ICIR) · doi:10.1109/icir68135.2025.11361561 · Cited by 2 · see citing works
“These standards driving Electronic Health Records (EHRs) are a cornerstone of modern healthcare systems, enabling clinicians to make informed, evidence-based decisions [1–4].”
Self-citationKlang, E., Sorin, V., Korfiatis, P. D., Sawant, A., Freeman, R., Charney, A. W., Nadkarni, G. N., & Glicksberg, B. S. (2026) · PLOS Digital Health · doi:10.1371/journal.pdig.0001326 · Cited by 1 · see citing works
Empowering clinical trial design with agentic intelligence and real-world data
Li, H., Pan, W., Rajendran, S., Zang, C., & Wang, F. (2026) · Nature Communications · doi:10.1038/s41467-026-74501-2 · Cited by 9 · see citing works
“Phi-4 and Gemma-3 exhibit moderate runtimes (20.95± 7.94 min, 25.87± 4.38 minutes, respectively), while DeepSeek-R1 shows higher variance and longer runtimes (31.36± 14.51minutes), largely attributable to its extended chain-of-thought reasoning and local inference latency.”
InfluentialXu, R., Lu, Y., Liu, C., Chen, Y., Sun, Y. V., Hu, X., Ho, J. C., & Yang, C. (2024) · PubMed · doi:10.48550/arxiv.2406.05682 · Cited by 1 · see citing works
Self-citationMemory Injection Attacks on LLM Agents via Query-Only Interaction
Dong, S., Xu, S., He, P., Li, Y., Tang, J., Liu, T., Liu, H., & Xiang, Z. (2025) · arXiv · doi:10.48550/arxiv.2503.03704 · Cited by 1 · see citing works
“To validate the soundness of our experimental setup, we first clarify that similarity-based memory retrieval is a scalable and widely adopted strategy across LLM-based agents (e.g., RAP [20], EHR Agent [29]).”
InfluentialA-MemGuard: A Proactive Defense Framework for LLM-Based Agent Memory
Wei, Q., Yang, T., Wang, Y., Li, X., Li, L., Yin, Z., Zhan, Y., Holz, T., Lin, Z., & Wang, X. (2025) · arXiv · doi:10.48550/arxiv.2510.02373 · Cited by 1 · see citing works
Ahmad, H. F., Sajid, J., Rasool, R. U., & Malik, A. W. (2025) · Cluster Computing · doi:10.1007/s10586-025-05793-0
Datta, R., Cui, J., Guan, Z., Reddy, V., Eby, J. C., Madden, G. R., Silwal, R., & Vullikanti, A. K. S. (2026) · JMIR AI · doi:10.2196/88356 · Cited by 4 · see citing works
“…a powerful means to process such notes, especially when combined with large biomedical datasets to capture richer semantics beyond keywords and embeddings [15,21-23], they still face significant limitations, such as hallucinations, factual inaccuracies, and inadequate domain grounding [15,21].”
Tian, J., Li, L., Ye, W., Wang, H., Wang, L., Yu, L., Ren, Z., Chen, G., & Zhao, J. (2026) · World Wide Web · doi:10.1007/s11280-025-01399-z
A comprehensive survey on table question answering: Datasets, methods and future directions
Xu, W., Liu, Y., Lu, L., Li, H., & Sun, G. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.114459
RGPO: Ranking-Guided Preference Optimization for Reliable Clinical Reasoning
Hsu, C. T., Ding, J.-E., Hsu, H.-L., Hsu, C.-H., Yang, S., Yao, L.-H., Liao, C.-C., Liu, F., & Hung, F. (2026) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2026.3688221
“LLMs have been used for medical tasks like knowledge-based question answering, diagnostic reasoning on clinical vignettes, and patient-specific reasoning over electronic health records (EHRs) [18], [19], [20].”
DraftNEPABench: A Benchmark for Drafting NEPA Document Sections with Coding Agents
Acharya, A., Lakha, B., Meyur, R., Nuttall, R., Chaturvedi, S., Halappanavar, A., Hare, L., Zeng, L., Parker, M., Munikoti, S., et al. (2026) · ACM Conference on AI and Agentic Systems (CAIS) · doi:10.1145/3786335.3813132
Ferreira, J. C., & Gonçalves, F. (2026) · Journal of Sports Analytics · doi:10.1177/22150218261448184
Towards Autonomous Personal Health Knowledge Graphs Through Multi-agent Collaboration
Cola, C., Costea, C., & Vălean, H. (2026) · World Congress on Medical Physics and Biomedical Engineering, September 7 - 12, 2009, Munich, Germany · doi:10.1007/978-3-032-24724-7_35
Gensheimer, M. F., Adhikari, R., Parmer-Chow, C., et al. (2026) · medRxiv · doi:10.64898/2026.06.17.26355917
KGDAgents: A Knowledge Graph Enhanced Multi-agent Framework For Clinical Diagnosis
Chen, Y., Zhou, X., Qiao, X., Lian, Y., Zhang, W., Lü, W., Zhu, J., & Guo, J. (2026) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd68734.2026.11582439
“Furthermore, some studies have utilized multi-agent systems to process structured EHR data [15], [16], thus improving the efficiency of EHR data processing.”
Vatsal, S., Dubey, H., & Bajaj, A. (2026) · IEEE Access · doi:10.1109/access.2026.3720396
“EHRAgent [54] treats Electronic Health Record (EHR) reasoning as programmatic tool use: the agent generates and executes code, uses execution feedback to repair failures and retrieves successful traces as reusable long-term state for later problem instances.”
MACA-PA: A Modular Agent-based Clinical Assistant for Perioperative Anesthesia
Jiang, Y., Ma, C., Xu, Z.-Z., et al. (2026) · Proceedings of the 2026 2nd International Conference on Health Informatization and Data Analysis · doi:10.1145/3819113.3819136
Can a General-Purpose Coding Agent Analyze a Production Hospital Data Warehouse?Preprint
Marshall, N. P., Haberkorn, W. J., Faulkenberry, J., Palakkattil, G., Haredasht, F. N., Schwenk, H. T., Chen, J. H., & Morse, K. (2026) · medRxiv · doi:10.64898/2026.09.02.26362008
Zou, H., Wang, J., Yang, Z., Zhang, M., Li, Y., Du, W., Chen, J., Duan, Z. Y., & Zhao, S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37664-0_7
Doan, N. N., Elen, B., Sun, C., Dumontier, M., & Ertaylan, G. (2026) · doi:10.2196/preprints.112384
Data-reflector: an agentic exploratory data analysis platform for researchers
Sabounchi, M., Hazare, N. S., Capone, C., Jangda, M., Oh, W., Jayaraman, P., Gupta, S., Sawant, A., Kuschner, Z., Parchure, P., et al. (2026) · JAMIA Open · doi:10.1093/jamiaopen/ooag194
- Authors
- Shi, W., Xu, R., Zhuang, Y., Yu, Y., Zhang, J., Wu, H., Zhu, Y., Ho, J. C., Yang, C., & Wang, M. D.
- Affiliations
- Georgia Institute of Technology (US)
- Emory University (US)
- University of Washington (US)
- Venue
- Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
- Published
- 2024
- Volume
- 2024
- Pages
- 22315-22339
- PMC
- PMC11867733
- OpenAlex
- W4404781813
- Cited by
- 54
- References
- 66
- Citations by year
- 2026: 27 · 2025: 23 · 2024: 4
- FWCI
- 15.91
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Conference on Empirical Methods in Natural Language Processing (EMNLP) (publishedVersion, cc-by)
- PubMed (publishedVersion)
- PubMed Central (acceptedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Science Foundation (2319449, 2312502)
- Microsoft Research
- Emory University
- National Institutes of Health
- National Institute of Diabetes and Digestive and Kidney Diseases (K25DK135913)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Health Sciences › Health Professions › Health Information Management › Electronic Health Records Systems
- Keywords
- LLM agents, electronic health records, tabular reasoning, few-shot learning, code generation, natural language querying, clinical information extraction
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
