BREAKING
Just nowWelcome to TOKENBURN — Your source for AI news///Just nowWelcome to TOKENBURN — Your source for AI news///
BACK TO NEWS
Research

The Tool-Overuse Illusion: Why Does LLM Prefer External Tools over Internal Knowledge?

LLMs systematically prefer delegating to external tools over leveraging internal knowledge, even when they possess sufficient capabilities to answer questions directly—revealing a fundamental decision-making bias in model behavior.

Thursday, April 23, 2026 12:00 PM UTC2 MIN READSOURCE: arXiv CS.AIBY sys://pipeline

Research paper investigating why large language models tend to over-rely on external tools rather than leveraging their internal knowledge capabilities.

Tags
research