Lomekwi: Resource-Bounded Tool Discovery in LLM Agents

Abstract:Existing tool-use benchmarks report a single success rate for complex, multistep tasks. Inspired by ideas from cognitive science, we distinguish tool use from tool discovery and decompose the latter into curiosity (the model's ability to discover the parts needed to build the tool), recognition (the model's ability to discover the process of creating the tool), and efficiency (the model's use of the tool after creation). We show that this framework can be applied to existing discovery tasks, such as Voyager. In addition, we provide evidence that recognition inversely scales with model size, and we introduce and analyze a class of combinatorial games that demonstrates this. We further observe inverse scaling in a separate environment designed to emulate real-world tasks.

All authors contributed equally. 17 pages, 6 figures. Presented at the 2026 Conference on Learning Theory Workshop on Learning in an Agentic World

Artificial Intelligence (cs.AI)

I.2.6; I.2.11; I.2.7

arXiv:2607.16961 [cs.AI]

(or arXiv:2607.16961v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2607.16961 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.