mlsanityData to 14 Oct 2026

Lomekwi: Resource-Bounded Tool Discovery in LLM Agents

arXiv 2607.16961 ↗First posted 18 Jul 2026cs.AIcited by 0

On the map: LLM agents and tool use → Tool learning and function calling

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Tool learning and function calling, one of 16 directions in LLM agents and tool use. Builds on 10 of its 17 references that are in the map. First posted on arXiv 18 Jul 2026.

Builds on

10 of 17 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Tool Learning with Large Language Models: A Survey28 May
  2. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs31 Jul
  3. 2023Large Language Models as Tool Makers26 May
  4. 2023Gorilla: Large Language Model Connected with Massive APIs24 May

Other references · 6

  1. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,191
  2. 2023Inverse Scaling: When Bigger Isn't Bettercited by 207
  3. 2023CREATOR: Tool Creation for Disentangling Abstract and Concrete Reasoning of Large Language Modelscited by 93
  4. 2024Planning, Creation, Usage: Benchmarking LLMs for Comprehensive Tool Utilization in Real-World Complex Scenarioscited by 86
  5. 2022Inverse scaling can become U-shapedcited by 76
  6. 2026Benchmarking LLM Tool-Use in the Wildcited by 17

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026SING: Synthetic Intention Graph for Scalable Active Tool Discovery in LLM Agents
  2. 2026PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystems
  3. 2026DIVE: Scaling Diversity in Agentic Task Synthesis for Generalizable Tool Use
  4. 2026Tools Are Not Islands: Set-Level Tool Retrieval for LLM Agents via Query-Conditioned Hyperedge Prediction
  5. 2026SkillCraft: Can LLM Agents Learn to Use Tools Skillfully?
  6. 2025MCP-Zero: Active Tool Discovery for Autonomous LLM Agents
  7. 2026OpaqueToolsBench: Learning Nuances of Tool Behavior Through Interaction
  8. 2026MetaForge: A Self-Evolving Multimodal Agent that Retrieves, Adapts, and Forges Tools On Demand ↗