Architect
Mar 31, 2025 · Artificial Intelligence
A Comprehensive Study of Failure Modes in Large‑Language‑Model Based Multi‑Agent Systems
This paper presents a systematic investigation of failure patterns in LLM‑driven multi‑agent systems, introducing a 14‑type taxonomy (MASFT) derived from over 150 annotated dialogues, evaluating it with an LLM‑as‑a‑judge pipeline, and exploring modest intervention strategies while releasing all data and tools for future research.
AILLMagentic
0 likes · 29 min read