Multi-Agent Memory Inconsistency: Where Factual Conflicts Disappear in LLM Agents
Multi-agent delegation lets LLM systems distribute evidence collection across workers with separate contexts. This creates a consistency challenge: facts retrieved by workers may be missing from the evidence available to the lead for a joint conclusion. We introduce a benchmark and evidence-flow profiler for studying multi-agent memory inconsistency through controlled factual conflicts in Harvey LAB document-review tasks. Pooled across three models with comparable generation spending, requiring delegation increases retrieval of both conflicting claims from 50.2% to 68.7% relative to single-agent execution, yet conflict detection falls from 16.2% to 13.2%. Within this setting, workers report both claims for only 35.2% of retrieved pairs, and pooled matched comparisons show higher detection than single-agent execution when one worker reads both claims but lower detection when the claims are split across workers. Worker-to-lead handoffs are a central target for improving conflict detection in multi-agent LLMs.
Authors
- 于恒嘉
- Matrix Yao
- Wentao Ni (ORCID: https://orcid.org/0009-0002-7355-0073)
- Yimin Ding
- Wei-Ting Chen
- Zhongming Yu
- Jishen Zhao
- Cong Xu
- Fan Zhao
- Hejia Zhang
- Yijun Liu
- Xin Chen
Publication Details
- Journal
- arXiv (Cornell University)
- Published
- 2026-11-17
- DOI
- https://doi.org/10.48550/arxiv.2611.22245
- Primary Topic
- Topic Modeling
- Type
- preprint