FEAT: A Multi-Agent Forensic AI System with Domain-Adapted Large Language Model for Automated Cause-of-Death Analysis

2025/08/11 by Chen Shen, Wanqing Zhang, Shen, Chen +36
Arts and Humanities · Computer Science · Medicine · #Artificial Intelligence (cs.AI) #Autopsy Techniques and Outcomes #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Forensic Anthropology and Bioarchaeology Studies #Machine Learning (cs.LG) #Machine Learning in Healthcare #Multiagent Systems (cs.MA)

paper · pdf · doi:10.48550/arxiv.2508.07950

openalex publication_date 2025/08/11 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Forensic cause-of-death determination faces systemic challenges, including workforce shortages and diagnostic variability, particularly in high-volume systems like China's medicolegal infrastructure. We introduce FEAT (ForEnsic AgenT), a multi-agent AI framework that automates and standardizes death investigations through a domain-adapted large language model. FEAT's application-oriented architecture integrates: (i) a central Planner for task decomposition, (ii) specialized Local Solvers for evidence analysis, (iii) a Memory & Reflection module for iterative refinement, and (iv) a Global Solver for conclusion synthesis. The system employs tool-augmented reasoning, hierarchical retrieval-augmented generation, forensic-tuned LLMs, and human-in-the-loop feedback to ensure legal and medical validity. In evaluations across diverse Chinese case cohorts, FEAT outperformed state-of-the-art AI systems in both long-form autopsy analyses and concise cause-of-death conclusions. It demonstrated robust generalization across six geographic regions and achieved high expert concordance in blinded validations. Senior pathologists validated FEAT's outputs as comparable to those of human experts, with improved detection of subtle evidentiary nuances. To our knowledge, FEAT is the first LLM-based AI agent system dedicated to forensic medicine, offering scalable, consistent death certification while maintaining expert-level rigor. By integrating AI efficiency with human oversight, this work could advance equitable access to reliable medicolegal services while addressing critical capacity constraints in forensic systems.

Citations

• Qwen3 Technical Report
• Baichuan-M1: Pushing the Medical Capability of Large Language Models
• DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning
• The Llama 3 Herd of Models
• Large-vocabulary forensic pathological analyses via prototypical cross-modal contrastive learning
• MMedAgent: Learning to Use Medical Tools with Multi-modal Agent
• ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools
• MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Making
• AI Hospital: Benchmarking Large Language Models in a Multi-agent Medical Interaction Simulator
• Self-Discover: Large Language Models Self-Compose Reasoning Structures
• MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning
• LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examples
• Forensic Histopathological Recognition via a Context-Aware MIL Network Powered by Self-Supervised Contrastive Learning
• ClinicalGPT: Large Language Models Finetuned with Diverse Medical Data and Comprehensive Evaluation
• Tree of Thoughts: Deliberate Problem Solving with Large Language Models
• Generative Agents: Interactive Simulacra of Human Behavior
• Capabilities of GPT-4 on Medical Challenge Problems
• GPT-4 Technical Report
• ReAct: Synergizing Reasoning and Acting in Language Models
• BNAI, NO-TOKEN, and MIND-UNITY: Pillars of a Systemic Revolution in Artificial Intelligence
• Text and Code Embeddings by Contrastive Pre-Training
• Sequence Model with Self-Adaptive Sliding Window for Efficient Spoken Document Segmentation
• LoRA: Low-Rank Adaptation of Large Language Models
• Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
• Publicly Available Clinical BERT Embeddings

Related

• Large-vocabulary forensic pathological analyses via prototypical cross-modal contrastive learning
• A deep artificial neural network based model for underlying cause of death prediction from death certificates
• Towards Open Standards for Systemic Complexity in Digital Forensics
• <scp>AI</scp> as a decision support tool in forensic image analysis: A pilot study on integrating large language models into crime scene investigation workflows
• Haibu Mathematical-Medical Intelligent Agent:Enhancing Large Language Model Reliability in Medical Tasks via Verifiable Reasoning Chains