# Agents Trust Tools Too Much: Measuring Reliance on Unreliable Tools

**Published:** September 9, 2026
**Author:** Hoyeol Yang, Woojung Song, Taewon Kim, Jonghyun Song, Seoyeon Park, Yohan Jo
**Source:** arXiv — cs.AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/en/articles/agents-trust-tools-too-much-measuring-reliance-on-unreliable-tools

arXiv:2609.05587v1 Announce Type: new Abstract: Existing evaluations of tool-using agents primarily measure whether an agent can successfully complete diverse tasks with tools. These evaluations generally assume that tools return reliable information. However, tool returns in…

> From the original source: **arXiv — cs.AI**
> [Read full article at arXiv — cs.AI](https://arxiv.org/abs/2609.05587)

**Tags:** #arXiv

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*