analiza aiqbench
ClinSeekAgent advances clinical AI by enabling agents to actively query longitudinal EHR records and invoke imaging tools rather than relying on pre-curated evidence. This shift from passive consumption to active acquisition demonstrates significant performance gains over curated inputs for both frontier models like GPT-5.6 Sol and open-source variants trained on these trajectories. The work establishes a new benchmark, ClinSeek-Bench, that evaluates agentic reasoning across text-only and multimodal medical tasks without requiring manual evidence selection.
ClinSeekAgent: Automating Multimodal Evidence Seeking for Agentic Clinical Reasoning
arXiv:2605.20176v2 Announce Type: replace Abstract: Large language models (LLMs) and agentic systems have shown promise for clinical decision support, but existing works largely assume that evidence has already been curated and handed to the model. Real-world clinical workflows instead require agents to actively seek, iteratively plan, and synthesize multimodal evidence from heterogeneous sources. In this paper, we introduce ClinSeekAgent, an automated agentic framework for dynamic multimodal evidence seeking that shifts the paradigm from passive evidence consumption to active evidence acquisition. Given a clinical task and access to raw patient data, ClinSeekAgent queries longitudinal EHR records and invokes imaging analysis tools when relevant; refines its hypotheses as new information emerges; and integrates the collected evidence into grounded clinical decisions. We validate ClinSeekAgent in two roles: as an inference-time agent for frontier LLMs and as a training pipeline for open-source models. For inference-time validation, we construct ClinSeek-Bench, which covers 13 text-only EHR task categories and 6 multimodal EHR--chest X-ray task categories, and pairs each question with both a Curated Input of pre-selected evidence and the raw patient data for automated evidence seeking. Without any benchmark-specific curation, ClinSeekAgent significantly outperforms curated input for both Claude Opus 5 and GPT-5.6 Sol, improving overall F1 from 66.5 to 68.8 and from 60.0 to 62.5 on multimodal tasks. The ablations show that the performance gain come from multi-round evidence seeking rather than from access to more of the patient record. For training-time validation, we fine-tune Qwen3.5-35B-A3B on ClinSeekAgent trajectories generated by GPT-5.6 Sol. The resulting ClinSeek-35B-A3B reaches 35.6 average F1 on AgentEHR-Bench, outperforming all evaluated open-source models, including ones more than ten times larger, as well as Claude Opus 5.
Abstract:Large language models (LLMs) and agentic systems have shown promise for clinical decision support, but existing works largely assume that evidence has already been curated and handed to the model. Real-world clinical workflows instead require agents to actively seek, iteratively plan, and synthesize multimodal evidence from heterogeneous sources. In this paper, we introduce ClinSeekAgent, an automated agentic framework for dynamic multimodal evidence seeking that shifts the paradigm from passive evidence consumption to active evidence acquisition. Given a clinical task and access to raw patient data, ClinSeekAgent queries longitudinal EHR records and invokes imaging analysis tools when relevant; refines its hypotheses as new information emerges; and integrates the collected evidence into grounded clinical decisions. We validate ClinSeekAgent in two roles: as an inference-time agent for frontier LLMs and as a training pipeline for open-source models. For inference-time validation, we construct ClinSeek-Bench, which covers 13 text-only EHR task categories and 6 multimodal EHR--chest X-ray task categories, and pairs each question with both a Curated Input of pre-selected evidence and the raw patient data for automated evidence seeking. Without any benchmark-specific curation, ClinSeekAgent significantly outperforms curated input for both Claude Opus 5 and GPT-5.6 Sol, improving overall F1 from 66.5 to 68.8 and from 60.0 to 62.5 on multimodal tasks. The ablations show that the performance gain come from multi-round evidence seeking rather than from access to more of the patient record. For training-time validation, we fine-tune Qwen3.5-35B-A3B on ClinSeekAgent trajectories generated by GPT-5.6 Sol. The resulting ClinSeek-35B-A3B reaches 35.6 average F1 on AgentEHR-Bench, outperforming all evaluated open-source models, including ones more than ten times larger, as well as Claude Opus 5.
Computation and Language (cs.CL)
arXiv:2605.20176 [cs.CL]
(or arXiv:2605.20176v2 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2605.20176 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 362 cuvinte