[2603.00200] LiaisonAgent: An Multi-Agent Framework for Autonomous Risk Investigation and Governance

Computer Science > Cryptography and Security arXiv:2603.00200 (cs) [Submitted on 27 Feb 2026] Title:LiaisonAgent: An Multi-Agent Framework for Autonomous Risk Investigation and Governance Authors:Chuanming Tang, Ling Qing, Shifeng Chen View a PDF of the paper titled LiaisonAgent: An Multi-Agent Framework for Autonomous Risk Investigation and Governance, by Chuanming Tang and 2 other authors View PDF HTML (experimental) Abstract:The rapid evolution of sophisticated cyberattacks has strained modern Security Operations Centers (SOC), which traditionally rely on rule-based or signature-driven detection systems. These legacy frameworks often generate high volumes of technical alerts that lack organizational context, leading to analyst fatigue and delayed incident responses. This paper presents LiaisonAgent, an autonomous multi-agent system designed to bridge the gap between technical risk detection and business-level risk governance. Built upon the QWQ-32B large reasoning model, LiaisonAgent integrates specialized sub-agents, including human-computer interaction agents, comprehensive judgment agents, and automated disposal agents-to execute end-to-end investigation workflows. The system leverages a hybrid planning architecture that combines deterministic workflows for compliance with autonomous reasoning based on the ReAct paradigm to handle ambiguous operational scenarios. Experimental evaluations across diverse security contexts, such as large-scale data exfiltration and unau...