# Small Reasoning Models are Instruction Followers in Function Calling

arXiv: https://arxiv.org/abs/2608.22472 · HTML: https://mlsanity.com/paper/2608.22472/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 19 of its 29 references that are in the map.
- First posted on arXiv 23 Aug 2026.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)
- LLM agents and tool use / [Tool learning and function calling](https://mlsanity.com/agents/tool-learning-and-function-calling/)

## Builds on (most cited first, 19 of 19)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs](https://mlsanity.com/paper/2503.01743/) (2025)
- [ToolRL: Reward is All Tool Learning Needs](https://mlsanity.com/paper/2504.13958/) (2025)
- [Small Language Models are the Future of Agentic AI](https://mlsanity.com/paper/2506.02153/) (2025)
- [From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions](https://mlsanity.com/paper/2410.08197/) (2024)
- [AgentDistill: Training-Free Agent Distillation with Generalizable MCP Boxes](https://mlsanity.com/paper/2506.14728/) (2025)
- [Small Language Models for Agentic Systems: A Survey of Architectures, Capabilities, and Deployment Trade offs](https://mlsanity.com/paper/2510.03847/) (2025)
- [Routine: A Structural Planning Framework for LLM Agent System in Enterprise](https://mlsanity.com/paper/2507.14447/) (2025)
- [Small Language Models for Efficient Agentic Tool Calling: Outperforming Large Models with Targeted Fine-tuning](https://mlsanity.com/paper/2512.15943/) (2025)
- [Achieving Tool Calling Functionality in LLMs Using Only Prompt Engineering Without Fine-Tuning](https://mlsanity.com/paper/2407.04997/) (2024)
- [Beyond Scale: Small Language Models are Comparable to GPT-4 in Mental Health Understanding](https://mlsanity.com/paper/2507.08031/) (2025)
- [Optimizing Small Language Models for In-Vehicle Function-Calling](https://mlsanity.com/paper/2501.02342/) (2025)
- [Factored Agents: Decoupling In-Context Learning and Memorization for Robust Tool Use](https://mlsanity.com/paper/2503.22931/) (2025)
- [Enhancing Reasoning Capabilities of Small Language Models with Blueprints and Prompt Template Search](https://mlsanity.com/paper/2506.08669/) (2025)
- [Domain-Adaptive Small Language Models for Structured Tax Code Prediction](https://mlsanity.com/paper/2507.10880/) (2025)
- [Natural Language Tools: A Natural Language Approach to Tool Calling In Large Language Agents](https://mlsanity.com/paper/2510.14453/) (2025)
- [SLM-Based Agentic AI with P-C-G: Optimized for Korean Tool Use](https://mlsanity.com/paper/2509.19369/) (2025)

## Abstract (arXiv)

Function calling represents the core capability of agentic large language models (LLMs). Existing research has focused on enhancing LLMs function-calling accuracy through fine-tuning, reinforcement learning (RL), and multi-agent frameworks, particularly for native function-calling LLMs. This work demonstrates that LLMs achieve superior accuracy in function calling in instruction-following contexts (i.e., standard user-assistant interactions) rather than a tool calling context. We introduce Instruction-Followed Function Calling (IFFC), a novel framework that decouples function-calling logic from the primary LLM and delegates it to a dedicated smaller model operating within the instruction-following paradigm. Our method consistently outperforms both native function calling (NFC) and prompt-based function calling (PFC) baselines, with particularly strong gains on reasoning-oriented LLMs. Furthermore, we demonstrate that IFFC maintains robust performance under aggressive quantization, enabling efficient on-device deployment without significant accuracy degradation. This work establishes a new paradigm for reliable, resource-efficient function calling in edge-computing scenarios.