ClinSeekAgent: Automating Multimodal Evidence Seeking for Agentic Clinical Reasoning

• URL: http://arxiv.org/abs/2605.20176v1
• Date: Tue, 19 May 2026 17:58:37 GMT
• Title: ClinSeekAgent: Automating Multimodal Evidence Seeking for Agentic Clinical Reasoning
• Abstract summary: ClinSeekAgent is an automated agentic framework for dynamic multimodal evidence seeking.<n>Given only a clinical query and access to raw data sources, ClinSeekAgent gathers evidence by querying medical knowledge bases, navigating raw EHRs, and invoking medical imaging tools.
• Score: 49.05361955143476
• License: http://creativecommons.org/licenses/by/4.0/
• 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 only a clinical query and access to raw data sources, ClinSeekAgent gathers evidence by querying medical knowledge bases, navigating raw EHRs, and invoking medical imaging tools; refines its hypotheses as new information emerges; and integrates the collected evidence into grounded clinical decisions. ClinSeekAgent serves both as an inference-time agent for frontier LLMs and as a training-time pipeline for distilling high-quality agent trajectories into compact open-source models. To validate its inference-time effectiveness, we construct ClinSeek-Bench, which pairs Curated Input reasoning from fixed pre-selected evidence with Automated Evidence-Seeking over raw clinical data. On text-only EHR tasks, ClinSeekAgent improves Claude Opus 4.6 from 60.0 to 63.2 overall F1 and MiniMax M2.5 from 43.1 to 47.3, with positive risk-prediction gains in 7 out of 9 evaluated host models. On multimodal tasks, ClinSeekAgent improves Claude Opus 4.6 from 47.5 to 62.6 (+15.1); all evaluated models improve across the three CXR-related task groups. We further validate ClinSeekAgent as a training pipeline by distilling agentic evidence-seeking trajectories into ClinSeek-35B-A3B, which achieves 34.0 average F1 on existing AgentEHR-Bench, improving over its Qwen3.5-35B-A3B baseline by +11.9 points and approaching Claude Opus 4.6.

Related papers

• ClinAgent: A ReAct-Based Agent for Conversational Access to Clinical Trial Information [0.48861336570452174]
  We introduce ClinAgent, a conversational system based on agentic Retrieval-Augmented Generation (RAG)<n>The system centers on a Large Language Model (LLM) agent following the ReAct paradigm, which iteratively reasons over queries.<n>We evaluate the system using a three-phase framework assessing operational effectiveness, planning quality, tool-use efficiency, and expert qualitative judgments.
  arXiv  Detail & Related papers  (2026-09-12T10:25:35Z)
• NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness [76.6324710887112]
  NeoHorse-1 is a family of agent-native models developed to explore this path through agentic post-training.<n>Our system combines a heterogeneous model pool with intelligent routing, recording the predicted capability demand, selected service tier, and subsequent interaction for each user turn.
  arXiv  Detail & Related papers  (2026-09-08T03:14:54Z)
• ResidencyRL: Reinforcement Learning in Simulated Clinical Environments [53.76751756107077]
  We present ResidencyRL, a reinforcement learning (RL) method for training clinical artificial intelligence (AI) agents through simulated multi-turn clinical encounters.<n>On heldout evaluations, the ResidencyRL agent improves diagnostic accuracy by 7.0% under adversarial conditions.<n>Blinded expert clinicians validated these gains, preferring the trained agent in 87.6% of side-by-side comparisons.
  arXiv  Detail & Related papers  (2026-08-07T17:04:41Z)
• CuraView: A Multi-Agent Framework for Medical Hallucination Detection with GraphRAG-Enhanced Knowledge Verification [3.422186949568493]
  We present CuraView, a framework for sentence-level detection and evidence-grounded explanation of faithfulness hallucinations in discharge summaries.<n>CuraView constructs a GraphRAG-based knowledge graph from patient-level EHRs.<n>We evaluate CuraView on a subset of 250 patients from the Discharge-Me benchmark, with 50 patients held out for testing.
  arXiv  Detail & Related papers  (2026-05-05T08:05:31Z)
• RadAgent: A tool-using AI agent for stepwise interpretation of chest computed tomography [8.642043084168817]
  Vision-language models (VLM) have markedly advanced AI-driven interpretation and reporting of medical imaging, such as computed tomography (CT)<n>Yet, existing methods largely relegate clinicians to passive observers of final outputs, offering no interpretable reasoning trace for them to inspect, validate, or refine.<n>We introduce RadAgent, a tool-using AI agent that generates CT reports through a stepwise and interpretable process.
  arXiv  Detail & Related papers  (2026-04-16T17:09:30Z)
• Benchmarking Multi-turn Medical Diagnosis: Hold, Lure, and Self-Correction [72.89352076103889]
  Large language models (LLMs) achieve high accuracy in medical diagnosis when all clinical information is provided in a single turn.<n>We introduce MINT, a high-fidelity, multi-turn medical diagnosis benchmark comprising 1,035 cases.<n>We uncover three persistent behavioral patterns that significantly impact diagnostic decisions.
  arXiv  Detail & Related papers  (2026-04-06T00:23:10Z)
• AgentCPM-Explore: Realizing Long-Horizon Deep Exploration for Edge-Scale Agents [75.67445299298949]
  AgentCPM-Explore is a compact 4B agent model with high knowledge density and strong exploration capability.<n>We introduce a holistic training framework featuring parameter-space model fusion, reward signal denoising, and contextual information refinement.<n>AgentCPM-Explore achieves state-of-the-art (SOTA) performance among 4B-class models, matches or surpasses 8B-class SOTA models on four benchmarks, and even outperforms larger-scale models such as Claude-4.5-Sonnet or DeepSeek-v3.2 in five benchmarks.
  arXiv  Detail & Related papers  (2026-02-06T08:24:59Z)
• Strong Reasoning Isn't Enough: Evaluating Evidence Elicitation in Interactive Diagnosis [29.630872344186873]
  Interactive medical consultation requires an agent to proactively elicit missing clinical evidence under uncertainty.<n>Existing evaluations largely remain static or outcome-centric, neglecting the evidence-gathering process.<n>We propose an interactive evaluation framework that explicitly models the consultation process using a simulated patient and a revsimulated reporter grounded in atomic evidences.
  arXiv  Detail & Related papers  (2026-01-27T16:36:35Z)
• The Bitter Lesson of Diffusion Language Models for Agentic Workflows: A Comprehensive Reality Check [54.08619694620588]
  We present a comprehensive evaluation of dLLMs across two distinct agentic paradigms: Embodied Agents and Tool-Calling Agents.<n>Our results on Agentboard and BFCL reveal a "bitter lesson": current dLLMs fail to serve as reliable agentic backbones.
  arXiv  Detail & Related papers  (2026-01-19T11:45:39Z)
• UCAgents: Unidirectional Convergence for Visual Evidence Anchored Multi-Agent Medical Decision-Making [23.911343934512626]
  Vision-Language Models (VLMs) show promise in medical diagnosis, yet suffer from reasoning detachment.<n>Recent multi-agent frameworks simulate Multidisciplinary Team (MDT) debates to mitigate single-model bias.<n>We propose UCAgents to enforce unidirectional convergence through structured evidence auditing.
  arXiv  Detail & Related papers  (2025-12-02T07:20:21Z)
• Evolving Diagnostic Agents in a Virtual Clinical Environment [75.59389103511559]
  We present a framework for training large language models (LLMs) as diagnostic agents with reinforcement learning.<n>Our method acquires diagnostic strategies through interactive exploration and outcome-based feedback.<n>DiagAgent significantly outperforms 10 state-of-the-art LLMs, including DeepSeek-v3 and GPT-4o.
  arXiv  Detail & Related papers  (2025-10-28T17:19:47Z)
• DispatchMAS: Fusing taxonomy and artificial intelligence agents for emergency medical services [49.70819009392778]
  Large Language Models (LLMs) and Multi-Agent Systems (MAS) offer opportunities to augment dispatchers.<n>This study aimed to develop and evaluate a taxonomy-grounded, multi-agent system for simulating realistic scenarios.
  arXiv  Detail & Related papers  (2025-10-24T08:01:21Z)
• SelfCheckAgent: Zero-Resource Hallucination Detection in Generative Large Language Models [0.16385815610837165]
  SelfCheckAgent is a novel framework integrating three different agents.<n>These agents provide a robust multi-dimensional approach to hallucination detection.<n>The framework also incorporates a triangulation strategy, which increases the strengths of the SelfCheckAgent.
  arXiv  Detail & Related papers  (2025-02-03T20:42:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.