Expired50% confidenceFactExact time
Multiple studies in 2023 showed that in unconstrained multi-agent interactions, the system-level hallucination rate increases exponentially.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 9/30/2026(expired)
Sources
Related Claims
Unverified模型规模越大，幻觉的表述往往越流畅、越具迷惑性，识别难度反而上升71% similarUnverified当AI缺乏足够的项目上下文时，幻觉率会显著上升71% similarUnverifiedMulti-agent systems significantly amplify the uncertainty of LLMs; one agent's hallucination can contaminate the entire pipeline, making observability and error isolation design particularly critical69% similarUnverified研究表明即便是顶级模型，在工具调用链超过5步后幻觉率会显著上升，原因是早期错误随上下文传递被后续步骤合理化67% similarUnverified在并行多Agent场景下，单个代理的幻觉输出若未被及时纠正，可能通过文件依赖关系产生级联污染的放大效应67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/43724API
curl https://kongchang.com/api/v1/knowledge/claims/43724MCP
get_claim(id=43724)