This work proposes MRER (multi-agent reasoning with evidence retrieval), a multi-agent retrieval and reasoning framework inspired by evidence-based medicine that achieves an average accuracy and improves the logical coherence and trustworthiness of the generated reasoning.
Abstract
Although large language models have shown great promise in the medical domain, they still face challenges in complex medical reasoning tasks, including hallucinations and inconsistent reasoning. To address these challenges, we propose MRER (multi-agent reasoning with evidence retrieval), a multi-agent retrieval and reasoning framework inspired by evidence-based medicine. MRER employs a closed-loop adaptive reasoning process that uses accumulated evidence to identify unresolved evidence needs and guide targeted follow-up retrieval. Experimental results show that MRER achieves an average accuracy of 70.68% across three widely used medical benchmarks, representing an absolute improvement of 8.20% over the direct inference baseline. The framework enables a lightweight 8B open-source model to outperform a 70B medical domain-specific model and GPT-3.5 in our experiments. MRER also demonstrates adaptive, on-demand computation when handling complex queries. Human evaluation further indicates that MRER improves the logical coherence and trustworthiness of the generated reasoning. These findings suggest that incorporating evidence-based medicine principles into multi-agent collaboration can support the development of more evidence-grounded and scalable medical AI systems.
An adaptive memory and reflection (AMR) agentic system, a multi-agent framework in which specialized agents use dedicated memory and reflection-based feedback to retrieve relevant prior cases and improve subsequent reasoning.
Pr Murugesan, Luo-Xiao Yang, Xue-Li Chen et al.· 0 citations
EMR introduces a hierarchical clinical experience library that organizes accumulated knowledge into three levels: clinical principles, diagnostic patterns, and representative cases, and reveals that the hierarchical experience enables cross-specialty generalization and transfer across diverse LLM backbones, offering a...
This research proposes a comprehensive framework combining GraphRAG with dynamic retrieval selection, multi-modal knowledge graphs, decentralized multi-agent collaboration, and causal reasoning to address critical gap between computational methods and trustworthy recommendations.
Manish Rana· Natural Resources for Human...· 0 citations
MedTraj is proposed, a framework that treats reasoning trajectories as critical objects for construction, evaluation, and optimization, and quality-weighted context learning feeds trajectory evaluations back into the model at inference time, allowing it to learn from both strong and weak reasoning demonstrations.
Yun-Qi Zhu, Wen Tang, Jing-Hao Niu et al.· 0 citations
Multimodal clinical decision-making requires reliable reasoning over heterogeneous evidence from electronic health records, medical images, and physiological signals. Existing models typically map these inputs directly to diagnoses without explicitly assessing evidence sufficiency, tool-use requirements, or diagnostic...
Retrieval-Augmented Reasoning is presented, an architecture that embeds retrieval inside the reasoning workflow using a reasoning-state manager, retrieval-trigger decisions, evidence integration, and answer generation and shows that reasoning-guided retrieval improves answer completeness and reliability with manageable...
Ramesh Venkatachalapathy· 2026 6th International Confe...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.