# Toward SLM-based agentic task-tool intent matching

arXiv: https://arxiv.org/abs/2610.03213 · HTML: https://mlsanity.com/paper/2610.03213/

## 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 15 references that are in the map.
- First posted on arXiv 2 Oct 2026.

## Placed in

- LLM agents and tool use / [Tool learning and function calling](https://mlsanity.com/agents/tool-learning-and-function-calling/)

## Builds on (most cited first, 10 of 10)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Understanding R1-Zero-Like Training: A Critical Perspective](https://mlsanity.com/paper/2503.20783/) (2025)
- [GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning](https://mlsanity.com/paper/2507.19457/) (2025)
- [Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence](https://mlsanity.com/paper/2407.07061/) (2024)
- [TOUCAN: Synthesizing 1.5M Tool-Agentic Data from Real-World MCP Environments](https://mlsanity.com/paper/2510.01179/) (2025)
- [Delegated Authorization for Agents Constrained to Semantic Task-to-Scope Matching](https://mlsanity.com/paper/2510.26702/) (2025)
- [A Layered Protocol Architecture for the Internet of Agents](https://mlsanity.com/paper/2511.19699/) (2025)
- [Hybrid Inspection and Task-Based Access Control in Zero-Trust Agentic AI](https://mlsanity.com/paper/2605.02682/) (2026)

## Abstract (arXiv)

Tool-equipped AI agents use tool calls to access data and act on external systems. Horizontal growth of agentic systems increases the number of these interactions, and further motivates the need for automated, per-call oversight that can operate at low latency and/or on-prem. Conventional authorization schemes can determine whether an agent is allowed to invoke a tool, but cannot assess the agent's underlying cognition, specifically, whether the tool selection represents a logical, relevant step toward satisfying the intent of the task or not. Consequently, an allowed call may still deviate from the task's intent: a rogue agent might deviate the calls or nudge other agents to make a combination of calls that would not align with the intent of the task. Therefore, every call needs to be verified. In this study we investigate the applicability of Small Language Models (SLMs) to this purpose: an SLM functions as a task-tool relevance classifier that evaluates every selected tool independently against the assigned task and returns a relevance signal for downstream enforcement. Equipped with a novel dataset with multi-tool tasks whose required tools span distinct Model Context Protocol (MCP) servers, we used prompt-optimization, supervised fine-tuning, and reinforcement learning through GRPO to optimize and specialize SLMs.