Tool-augmented large language models (LLMs) have powered many applications. However, they are likely to suffer from knowledge conflict. In this paper, we propose a new type of knowledge conflict -- Tool-Memory Conflict (TMC), where the internal parametric knowledge contradicts with the external tool knowledge for tool-augmented LLMs. We find that existing LLMs, though powerful, suffer from TMC, especially on STEM-related tasks. We also uncover that under different conditions, tool knowledge and parametric knowledge may be prioritized differently. We then evaluate existing conflict resolving techniques, including prompting-based and RAG-based methods. Results show that none of these approaches can effectively resolve tool-memory conflicts.
@article{arxiv.2601.09760,
title = {Investigating Tool-Memory Conflicts in Tool-Augmented LLMs},
author = {Jiali Cheng and Rui Pan and Hadi Amiri},
journal= {arXiv preprint arXiv:2601.09760},
year = {2026}
}