TSAssistant: A Human-in-the-Loop Agentic Framework for Automated Target Safety Assessment

2026-04-26

AI Summary

This work addresses the challenges in target safety assessment (TSA)—a process heavily reliant on expert judgment, characterized by iterative workflows, and hindered by limited scalability and reproducibility. The authors propose a multi-agent framework that decomposes TSA report generation into specialized subtasks, integrating structured and unstructured biomedical evidence through a modular architecture, hierarchical instruction design, and human-in-the-loop collaboration. The system enables interactive corrections, cross-turn memory retention, and user interventions, ensuring toxicologists retain ultimate decision-making authority. By automating routine tasks while preserving expert oversight, the approach substantially reduces manual effort and enhances the efficiency, traceability, and reproducibility of TSA, yielding citation-ready, evidence-based reports.

Technology Category

• Multiagent Systems: Teamwork
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Humans and AI: Planning and Decision Support for Human-Machine Teams

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Target Safety Assessment (TSA) requires systematic integration of heterogeneous evidence, including genetic, transcriptomic, target homology, pharmacological, and clinical data, to evaluate potential safety liabilities of therapeutic targets. This process is inherently iterative and expert-driven, posing challenges in scalability and reproducibility. We present TSAssistant, a multi-agent framework designed to support TSA report drafting through a modular, section-based, and human-in-the-loop paradigm. The framework decomposes report generation into a coordinated pipeline of specialised subagents, each targeting a single TSA section. Specialised subagents retrieve structured and unstructured data as well as literature evidence from curated biomedical sources through standardised tool interfaces, producing individually citable, evidence-grounded sections. Agent behaviour is governed by a hierarchical instruction architecture comprising system prompts, domain-specific skill modules, and runtime user instructions. A key feature is an interactive refinement loop in which users may manually edit sections, append new information, upload additional sources, or re-invoke agents to revise specific sections, with the system maintaining conversational memory across iterations. TSAssistant is designed to reduce the mechanical burden of evidence synthesis and report drafting, supporting a hybrid model in which agentic AI augments evidence synthesis while toxicologists retain final decision authority.

Problem

• Target Safety Assessment
• heterogeneous evidence integration
• expert-driven evaluation
• scalability
• reproducibility

Innovation

• multi-agent framework
• human-in-the-loop
• target safety assessment
• evidence synthesis
• modular report generation