Lomekwi: Resource-Bounded Tool Discovery in LLM Agents

• URL: http://arxiv.org/abs/2607.16961v1
• Date: Sat, 18 Jul 2026 20:40:13 GMT
• Title: Lomekwi: Resource-Bounded Tool Discovery in LLM Agents
• Abstract summary: We decompose tool use into curiosity, recognition, and efficiency.<n>We show that this framework can be applied to existing discovery tasks, such as Voyager.
• Score: 2.06749085915751
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• SciToolAgent-Evo: An Ontology-Aware Self-Evolving Agent for Open-World Scientific Tool Acquisition [53.36281538053445]
  We propose SciToolAgent-Evo, an ontology-aware self-evolving agent for open-world scientific tool acquisition.<n> Driven by an evolving memory of skills, experiences, and an ontologized tool graph, it distills generalizable knowledge from contrastive trajectories during accumulation.<n>Once a novel tool is acquired, its scientific knowledge is completed online for seamless integration into the known graph.
  arXiv  Detail & Related papers  (2026-07-30T08:47:11Z)
• SING: Synthetic Intention Graph for Scalable Active Tool Discovery in LLM Agents [64.59100414726556]
  Large language model (LLM) agents increasingly rely on harnesses that manage context, tools, and multi-turn execution.<n>Retrieval-augmented tool selection offers a natural alternative, but existing one-shot retrieval methods fail to align isolated tool descriptions with the agent's true task intention.<n>We propose SING, an intention-aware active tool discovery framework that builds an intention-tool graph linking user intentions, tool capabilities, and tool collaboration patterns.
  arXiv  Detail & Related papers  (2026-06-15T11:37:37Z)
• Creative Robot Tool Use by Counterfactual Reasoning [12.0843035300871]
  We propose a causal reasoning framework for creative robot tool use where a suitable tool for a task is correctly identified for use beyond its primary objectives.<n>We decouple the causal discovery problem into two complementary components: VLM-based feature suggestion and counterfactual tool generation.<n>By reconstructing the task in a dynamics model, our approach grounds tool use in the physics of the problem.
  arXiv  Detail & Related papers  (2026-05-06T20:10:28Z)
• PORTool: Tool-Use LLM Training with Rewarded Tree [11.154654446183455]
  We propose a reinforcement learning (RL) method that encourages a tool-use LLM to explore various trajectories yielding the correct answer.<n>A shared step across different trajectories receives the same reward, while different steps under the same fork receive different rewards.<n>Experiments utilize 17 tools to address user queries, covering both time-sensitive and time-invariant topics.
  arXiv  Detail & Related papers  (2025-10-29T23:28:53Z)
• ToolLibGen: Scalable Automatic Tool Creation and Aggregation for LLM Reasoning [80.10274552177096]
  Large Language Models (LLMs) equipped with external tools have demonstrated enhanced performance on complex reasoning tasks.<n>The widespread adoption of this tool-augmented reasoning is hindered by the scarcity of domain-specific tools.<n>We propose a systematic approach to automatically an unstructured collection of tools into a structured tool library.
  arXiv  Detail & Related papers  (2025-10-09T04:11:16Z)
• ToolACE-DEV: Self-Improving Tool Learning via Decomposition and EVolution [77.86222359025011]
  We propose ToolACE-DEV, a self-improving framework for tool learning.<n>First, we decompose the tool-learning objective into sub-tasks that enhance basic tool-making and tool-using abilities.<n>We then introduce a self-evolving paradigm that allows lightweight models to self-improve, reducing reliance on advanced LLMs.
  arXiv  Detail & Related papers  (2025-05-12T12:48:30Z)
• LLM With Tools: A Survey [0.0]
  This paper delves into the methodology,challenges, and developments in the realm of teaching LLMs to use external tools. We introduce a standardized paradigm for tool integration guided by a series of functions that map user instructions to actionable plans. Our exploration reveals the various challenges encountered, such as tool invocation timing, selection accuracy, and the need for robust reasoning processes.
  arXiv  Detail & Related papers  (2024-09-24T14:08:11Z)
• Towards Completeness-Oriented Tool Retrieval for Large Language Models [60.733557487886635]
  Real-world systems often incorporate a wide array of tools, making it impractical to input all tools into Large Language Models. Existing tool retrieval methods primarily focus on semantic matching between user queries and tool descriptions. We propose a novel modelagnostic COllaborative Learning-based Tool Retrieval approach, COLT, which captures not only the semantic similarities between user queries and tool descriptions but also takes into account the collaborative information of tools.
  arXiv  Detail & Related papers  (2024-05-25T06:41:23Z)
• Learning Generalizable Tool-use Skills through Trajectory Generation [13.879860388944214]
  We train a single model on four different deformable object manipulation tasks. The model generalizes to various novel tools, significantly outperforming baselines. We further test our trained policy in the real world with unseen tools, where it achieves the performance comparable to human.
  arXiv  Detail & Related papers  (2023-09-29T21:32:42Z)
• Tool Learning with Foundation Models [158.8640687353623]
  With the advent of foundation models, AI systems have the potential to be equally adept in tool use as humans. Despite its immense potential, there is still a lack of a comprehensive understanding of key challenges, opportunities, and future endeavors in this field.
  arXiv  Detail & Related papers  (2023-04-17T15:16:10Z)
• TANGO: Commonsense Generalization in Predicting Tool Interactions for Mobile Manipulators [15.61285199988595]
  We introduce TANGO, a novel neural model for predicting task-specific tool interactions. TANGO encodes the world state comprising of objects and symbolic relationships between them using a graph neural network. We show that by augmenting the representation of the environment with pre-trained embeddings derived from a knowledge-base, the model can generalize effectively to novel environments.
  arXiv  Detail & Related papers  (2021-05-05T18:11:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.