ClinAgent: A ReAct-Based Agent for Clinical Trial Information
ClinAgent: A ReAct-Based Agent for Conversational Access to Clinical Trial Information
This research provides a detailed evaluation of agentic AI systems for clinical trial information, comparing the performance of Gemini 3.0 Flash and DeepSeek V3.2 variants, which is useful for anyone interested in the practical application of AI in biomedical research.
This paper introduces ClinAgent, a conversational system based on agentic Retrieval-Augmented Generation (RAG) that allows clinicians and researchers to query clinical trial information in plain language.
The system uses a Large Language Model (LLM) agent following the ReAct paradigm, which iteratively reasons over queries, selects tools like ClinicalTrials.
gov and PubMed, and refines its actions.It was evaluated using a three-phase framework, comparing three LLM backends: Gemini 3.
0 Flash and two variants of DeepSeek V3.2.
Results show that DeepSeek (thinking mode) excels in planning quality, while Gemini achieves the highest overall performance and strongest expert ratings.
ClinAgent: A ReAct-Based Agent for Conversational Access to Clinical Trial Information
Querying clinical trial registries remains a manual and error-prone process, requiring researchers to navigate large volumes of semi-structured data without support for natural language interaction or cross-source synthesis. To address this, we introduce ClinAgent, a conversational system based on agentic Retrieval-Augmented Generation (RAG) that enables clinicians and researchers to query clinical trial information in plain language and receive grounded, up-to-date responses across multi-turn interactions. The system centers on a Large Language Model (LLM) agent following the ReAct paradigm, which iteratively reasons over queries, selects among a set of integrated tools, and refines its actions based on intermediate outputs. These tools include a ClinicalTrials.gov search interface, a PubMed module, and a Python-based analyzer operating on a locally cached structured dataset of clinical trials. We evaluate the system using a three-phase framework assessing operational effectiveness, planning quality, tool-use efficiency, and expert qualitative judgments, comparing three LLM backends: Gemini 3.0 Flash and two variants of DeepSeek V3.2 (thinking and non-thinking). Results reveal complementary strengths, with DeepSeek (thinking mode) excelling in planning quality, while Gemini achieves the highest overall performance and strongest expert ratings. Overall, our findings highlight the potential of agentic AI systems to improve the accessibility and synthesis of clinical trial information, supporting more efficient and user-centered biomedical research workflows.
This report is categorized under AITOP's "Papers" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include ClinAgent, ReAct, clinical research, RAG.
Primary source verification: published directly by arXiv: DeepSeek with first-party authority.
