[2506.00886] Position: Agent Should Invoke External Tools ONLY When Epistemically Necessary

Computer Science > Artificial Intelligence arXiv:2506.00886 (cs) [Submitted on 1 Jun 2025 (v1), last revised 8 May 2026 (this version, v4)] Title:Position: Agent Should Invoke External Tools ONLY When Epistemically Necessary Authors:Hongru Wang, Cheng Qian, Manling Li, Jiahao Qiu, Boyang Xue, Mengdi Wang, Heng Ji, Amos Storkey, Kam-Fai Wong View a PDF of the paper titled Position: Agent Should Invoke External Tools ONLY When Epistemically Necessary, by Hongru Wang and 8 other authors View PDF HTML (experimental) Abstract:As large language models evolve into tool-augmented agents, a central question remains unresolved: when is external tool use actually justified? Existing agent frameworks typically treat tools as ordinary actions and optimize for task success or reward, offering little principled distinction between epistemically necessary interaction and unnecessary delegation. This position paper argues that agents should invoke external tools only when epistemically necessary. Here, epistemic necessity means that a task cannot be completed reliably via the agent's internal reasoning over its current context, without any external interaction. We introduce the Theory of Agent (ToA), a framework that treats agents as making sequential decisions about whether remaining uncertainty should be resolved internally or delegated externally. From this perspective, common agent failure modes (e.g., overthinking and overacting) arise from miscalibrated decisions under uncertainty ra...