多智能体LLM对话的定向可追溯调查：基于知识图谱的语义捆绑
Targeted and Traceable Investigation of Multi-Agent LLM Dialogue via Semantic Bundling of Knowledge Graphs
浏览论文内容
中文总结 AI 辅助
针对多智能体LLM对话分析难题，提出将对话转为知识图谱并借助AgentK可视化系统进行语义捆绑，实现快速识别行动者与精准归因，并在VAST Challenge 2026 MC1数据集上验证有效性。
中文摘要 AI 辅助
当今多智能体LLM系统日益自动化，将LLM与LLM之间的交互记录为对话转录文本。然而，分析此类对话以获取洞察仍具挑战性，包括将行为归因于正确的行动者，以及总结长时间交流中的交互。我们提出了一种针对多智能体LLM对话的定向且可追溯的调查方法，并将其应用于VAST Challenge 2026 MC1数据集。该挑战要求参与者重建并解释TenantThread（一家房地产科技公司）中AI智能体之间的哪些内部通信导致了不当信息泄露。我们首先将对话转换为知识图谱（KG），然后使用AgentK（一种用于节点和边交互式语义捆绑的可视分析系统）对其进行调查。我们发现，我们的方法直接解决了两个主要挑战：（1）KG结构使用户能够更快地识别值得调查的行动者；（2）仅总结感兴趣行动者周围的区域，比阅读原始对话更好地支持按行动者进行归因。
英文摘要
Multi-agent LLM systems today are increasingly automated, logging LLM-LLM interactions as conversational transcripts. Yet analyzing such dialogue for insights remains challenging, including attributing behaviors to the correct actor and summarizing interactions across a long exchange. We present a targeted and traceable approach to investigating multi-agent LLM dialogue, applied to the VAST Challenge 2026 MC1 dataset. The challenge asks participants to reconstruct and explain which internal communications among AI agents at TenantThread, a property tech company, led to an inappropriate information release. We first convert the dialogue into a knowledge graph (KG) and then investigate it with AgentK, a visual analytics system for interactive Semantic Bundling of nodes and edges. We found that our approach directly addresses two main challenges: (1) the KG structure enables users to identify actors worth investigating faster; and (2) summarizing only the region surrounding an actor of interest better supports per-actor attribution than reading raw conversations.
发表机构
- Georgia Institute of Technology（佐治亚理工学院）
机构由 AI 辅助整理，请以论文原文为准。
