ReflecTool: Towards Reflection-Aware Tool-Augmented Clinical Agents

• URL: http://arxiv.org/abs/2410.17657v1
• Date: Wed, 23 Oct 2024 08:19:18 GMT
• Title: ReflecTool: Towards Reflection-Aware Tool-Augmented Clinical Agents
• Abstract summary: Large Language Models (LLMs) have shown promising potential in the medical domain. ClinicalAgent Bench(CAB) is a comprehensive medical agent benchmark consisting of 18 tasks across five key realistic clinical dimensions. ReflecTool is a novel framework that excels at utilizing domain-specific tools within two stages.
• Score: 22.596827147978598
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) have shown promising potential in the medical domain, assisting with tasks like clinical note generation and patient communication. However, current LLMs are limited to text-based communication, hindering their ability to interact with diverse forms of information in clinical environments. Despite clinical agents succeeding in diverse signal interaction, they are oriented to a single clinical scenario and hence fail for broader applications. To evaluate clinical agents holistically, we propose ClinicalAgent Bench~(CAB), a comprehensive medical agent benchmark consisting of 18 tasks across five key realistic clinical dimensions. Building on this, we introduce ReflecTool, a novel framework that excels at utilizing domain-specific tools within two stages. The first optimization stage progressively enlarges a long-term memory by saving successful solving processes and tool-wise experience of agents in a tiny pre-defined training set. In the following inference stage, ReflecTool can search for supportive successful demonstrations from already built long-term memory to guide the tool selection strategy, and a verifier improves the tool usage according to the tool-wise experience with two verification methods--iterative refinement and candidate selection. Extensive experiments on ClinicalAgent Benchmark demonstrate that ReflecTool surpasses the pure LLMs with more than 10 points and the well-established agent-based methods with 3 points, highlighting its adaptability and effectiveness in solving complex clinical tasks.

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)
• MedCTA: A Benchmark for Clinical Tool Agents [47.47354499871572]
  We introduce MedCTA, a benchmark for evaluating medical tool agents on clinician-validated, step-implicit tasks.<n>MedCTA comprises 107 real-world clinical tasks with clinician-verified executable trajectories over 5 deployed tools.<n>We benchmark 18 open- and closed-source multimodal models and find that even frontier systems remain brittle in multi-step clinical tool use.
  arXiv  Detail & Related papers  (2026-06-10T06:26:52Z)
• CAREAgent: Clinical Agent with Structured Reasoning and Tool-Integrated for Order Generation [10.3425347749644]
  Existing agents mainly focus on coarse-grained decisions and overlook the fine-grained, executable information required for clinical orders.<n>To address this gap, we propose CAREAgent, an agent for clinical order generation.<n>To support its training, we introduce a two-stage agentic reasoning data construction method.<n>Building on the constructed data, the model is first trained via supervised fine-tuning to acquire fundamental reasoning formats and medical knowledge.
  arXiv  Detail & Related papers  (2026-05-31T08:31:36Z)
• Evolving Medical Imaging Agents via Experience-driven Self-skill Discovery [26.23353599153354]
  MACRO is a self-evolving, experience-augmented medical agent that shifts from static tool composition to experience-driven tool discovery.<n>A lightweight image-feature memory grounds tool selection in a visual-clinical context, while a GRPO-like training loop reinforces reliable invocation of discovered composites.
  arXiv  Detail & Related papers  (2026-03-06T03:34:47Z)
• MedSAM-Agent: Empowering Interactive Medical Image Segmentation with Multi-turn Agentic Reinforcement Learning [53.37068897861388]
  MedSAM-Agent is a framework that reformulates interactive segmentation as a multi-step autonomous decision-making process.<n>We develop a two-stage training pipeline that integrates multi-turn, end-to-end outcome verification.<n>Experiments across 6 medical modalities and 21 datasets demonstrate that MedSAM-Agent achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-02-03T09:47:49Z)
• Generalist Large Language Models Outperform Clinical Tools on Medical Benchmarks [1.2773749417703923]
  Generalist models consistently outperformed clinical tools.<n>OpenEvidence and UpToDate Expert AI demonstrated deficits in completeness, communication quality, context awareness, and systems-based safety reasoning.
  arXiv  Detail & Related papers  (2025-12-01T02:14:43Z)
• Timely Clinical Diagnosis through Active Test Selection [49.091903570068155]
  We propose ACTMED (Adaptive Clinical Test selection via Model-based Experimental Design) to better emulate real-world diagnostic reasoning.<n>LLMs act as flexible simulators, generating plausible patient state distributions and supporting belief updates without requiring structured, task-specific training data.<n>We evaluate ACTMED on real-world datasets and show it can optimize test selection to improve diagnostic accuracy, interpretability, and resource use.
  arXiv  Detail & Related papers  (2025-10-21T18:10:45Z)
• MedGUIDE: Benchmarking Clinical Decision-Making in Large Language Models [10.46932473088646]
  We introduce MedGUIDE, a new benchmark for evaluating Large Language Models (LLMs) on their ability to make guideline-consistent clinical decisions.<n> MedGUIDE is constructed from 55 curated NCCN decision trees across 17 cancer types.<n>We apply a two-stage quality selection process, combining expert-labeled reward models and LLM-as-a-judge ensembles across ten clinical and linguistic criteria, to select 7,747 high-quality samples.
  arXiv  Detail & Related papers  (2025-05-16T18:21:52Z)
• A Multimodal Multi-Agent Framework for Radiology Report Generation [2.1477122604204433]
  Radiology report generation (RRG) aims to automatically produce diagnostic reports from medical images.<n>We propose a multimodal multi-agent framework for RRG that aligns with the stepwise clinical reasoning workflow.
  arXiv  Detail & Related papers  (2025-05-14T20:28:04Z)
• Medchain: Bridging the Gap Between LLM Agents and Clinical Practice through Interactive Sequential Benchmarking [58.25862290294702]
  We present MedChain, a dataset of 12,163 clinical cases that covers five key stages of clinical workflow. We also propose MedChain-Agent, an AI system that integrates a feedback mechanism and a MCase-RAG module to learn from previous cases and adapt its responses.
  arXiv  Detail & Related papers  (2024-12-02T15:25:02Z)
• Demystifying Large Language Models for Medicine: A Primer [50.83806796466396]
  Large language models (LLMs) represent a transformative class of AI tools capable of revolutionizing various aspects of healthcare. This tutorial aims to equip healthcare professionals with the tools necessary to effectively integrate LLMs into clinical practice.
  arXiv  Detail & Related papers  (2024-10-24T15:41:56Z)
• Towards Evaluating and Building Versatile Large Language Models for Medicine [57.49547766838095]
  We present MedS-Bench, a benchmark designed to evaluate the performance of large language models (LLMs) in clinical contexts. MedS-Bench spans 11 high-level clinical tasks, including clinical report summarization, treatment recommendations, diagnosis, named entity recognition, and medical concept explanation. MedS-Ins comprises 58 medically oriented language corpora, totaling 13.5 million samples across 122 tasks.
  arXiv  Detail & Related papers  (2024-08-22T17:01:34Z)
• AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environments [2.567146936147657]
  We introduce AgentClinic, a multimodal agent benchmark for evaluating large language models (LLM) in simulated clinical environments. We find that solving MedQA problems in the sequential decision-making format of AgentClinic is considerably more challenging, resulting in diagnostic accuracies that can drop to below a tenth of the original accuracy.
  arXiv  Detail & Related papers  (2024-05-13T17:38:53Z)
• Large Language Models in the Clinic: A Comprehensive Benchmark [63.21278434331952]
  We build a benchmark ClinicBench to better understand large language models (LLMs) in the clinic. We first collect eleven existing datasets covering diverse clinical language generation, understanding, and reasoning tasks. We then construct six novel datasets and clinical tasks that are complex but common in real-world practice. We conduct an extensive evaluation of twenty-two LLMs under both zero-shot and few-shot settings.
  arXiv  Detail & Related papers  (2024-04-25T15:51:06Z)
• ClinicalAgent: Clinical Trial Multi-Agent System with Large Language Model-based Reasoning [16.04933261211837]
  Large Language Models (LLMs) and multi-agent systems have shown impressive capabilities in natural language tasks but face challenges in clinical trial applications. We introduce Clinical Agent System (ClinicalAgent), a clinical multi-agent system designed for clinical trial tasks.
  arXiv  Detail & Related papers  (2024-04-23T06:30:53Z)
• AgentMD: Empowering Language Agents for Risk Prediction with Large-Scale Clinical Tool Learning [11.8292941452582]
  We introduce AgentMD, a novel language agent capable of curating and applying clinical calculators across various clinical contexts. AgentMD has automatically curated a collection of 2,164 diverse clinical calculators with executable functions and structured documentation, collectively named RiskCalcs. Manual evaluations show that RiskCalcs tools achieve an accuracy of over 80% on three quality metrics.
  arXiv  Detail & Related papers  (2024-02-20T18:37:19Z)
• AI Hospital: Benchmarking Large Language Models in a Multi-agent Medical Interaction Simulator [69.51568871044454]
  We introduce textbfAI Hospital, a framework simulating dynamic medical interactions between emphDoctor as player and NPCs. This setup allows for realistic assessments of LLMs in clinical scenarios. We develop the Multi-View Medical Evaluation benchmark, utilizing high-quality Chinese medical records and NPCs.
  arXiv  Detail & Related papers  (2024-02-15T06:46:48Z)
• Self-Verification Improves Few-Shot Clinical Information Extraction [73.6905567014859]
  Large language models (LLMs) have shown the potential to accelerate clinical curation via few-shot in-context learning. They still struggle with issues regarding accuracy and interpretability, especially in mission-critical domains such as health. Here, we explore a general mitigation framework using self-verification, which leverages the LLM to provide provenance for its own extraction and check its own outputs.
  arXiv  Detail & Related papers  (2023-05-30T22:05:11Z)
• VBridge: Connecting the Dots Between Features, Explanations, and Data for Healthcare Models [85.4333256782337]
  VBridge is a visual analytics tool that seamlessly incorporates machine learning explanations into clinicians' decision-making workflow. We identified three key challenges, including clinicians' unfamiliarity with ML features, lack of contextual information, and the need for cohort-level evidence. We demonstrated the effectiveness of VBridge through two case studies and expert interviews with four clinicians.
  arXiv  Detail & Related papers  (2021-08-04T17:34:13Z)

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.