# FunReason: Enhancing Large Language Models' Function Calling via Self-Refinement Multiscale Loss and Automated Data Refinement

arXiv: https://arxiv.org/abs/2505.20192 · HTML: https://mlsanity.com/paper/2505.20192/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 30 of its 55 references that are in the map.
- First posted on arXiv 26 May 2025.

## 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, 30 of 30)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs](https://mlsanity.com/paper/2304.08244/) (2023)
- [Reasoning Models Don't Always Say What They Think](https://mlsanity.com/paper/2505.05410/) (2025)
- [ToolRL: Reward is All Tool Learning Needs](https://mlsanity.com/paper/2504.13958/) (2025)
- [ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities](https://mlsanity.com/paper/2408.04682/) (2024)
- [APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay](https://mlsanity.com/paper/2504.03601/) (2025)
- [Evaluation of OpenAI o1: Opportunities and Challenges of AGI](https://mlsanity.com/paper/2409.18486/) (2024)
- [xLAM: A Family of Large Action Models to Empower AI Agent Systems](https://mlsanity.com/paper/2409.03215/) (2024)
- [Faithfulness vs. Plausibility: On the (Un)Reliability of Explanations from Large Language Models](https://mlsanity.com/paper/2402.04614/) (2024)
- [Tool-Star: Empowering LLM-Brained Multi-Tool Reasoner via Reinforcement Learning](https://mlsanity.com/paper/2505.16410/) (2025)
- [Nemotron-Research-Tool-N1: Exploring Tool-Using Language Models with Reinforced Reasoning](https://mlsanity.com/paper/2505.00024/) (2025)
- [LLM With Tools: A Survey](https://mlsanity.com/paper/2409.18807/) (2024)
- [HumanEval Pro and MBPP Pro: Evaluating Large Language Models on Self-invoking Code Generation](https://mlsanity.com/paper/2412.21199/) (2024)
- [InSpire: Vision-Language-Action Models with Intrinsic Spatial Reasoning](https://mlsanity.com/paper/2505.13888/) (2025)
- [An LLM-Tool Compiler for Fused Parallel Function Calling](https://mlsanity.com/paper/2405.17438/) (2024)
- [ToolACE-R: Model-aware Iterative Training and Adaptive Refinement for Tool Learning](https://mlsanity.com/paper/2504.01400/) (2025)
- [Small Models, Big Tasks: An Exploratory Empirical Study on Small Language Models for Function Calling](https://mlsanity.com/paper/2504.19277/) (2025)
- [Translating Regulatory Clauses into Executable Codes for Building Design Checking via Large Language Model Driven Function Matching and Composing](https://mlsanity.com/paper/2308.08728/) (2023)
- [Mitigating Training Imbalance in LLM Fine-Tuning via Selective Parameter Merging](https://mlsanity.com/paper/2410.03743/) (2024)

## Built on by (most cited first, 5 of 5)

- [FunReason-MT Technical Report: Advanced Data Synthesis Solution for Real-world Multi-Turn Tool-use](https://mlsanity.com/paper/2510.24645/) (2025)
- [Reasoning through Exploration: A Reinforcement Learning Framework for Robust Function Calling](https://mlsanity.com/paper/2508.05118/) (2025)
- [AWPO: Enhancing Tool-Use of Large Language Models through Adaptive Integration of Reasoning Rewards](https://mlsanity.com/paper/2512.19126/) (2025)
- [Try, Check and Retry: A Divide-and-Conquer Framework for Boosting Long-context Tool-Calling Performance of LLMs](https://mlsanity.com/paper/2603.11495/) (2026)
- [R2IF: Aligning Reasoning with Decisions via Composite Rewards for Interpretable LLM Function Calling](https://mlsanity.com/paper/2604.20316/) (2026)

## Abstract (arXiv)

The integration of large language models (LLMs) with function calling has emerged as a crucial capability for enhancing their practical utility in real-world applications. However, effectively combining reasoning processes with accurate function execution remains a significant challenge. Traditional training approaches often struggle to balance the detailed reasoning steps with the precision of function calls, leading to suboptimal performance. To address these limitations, we introduce FunReason, a novel framework that enhances LLMs' function calling capabilities through an automated data refinement strategy and a Self-Refinement Multiscale Loss (SRML) approach. FunReason leverages LLMs' natural reasoning abilities to generate high-quality training examples, focusing on query parseability, reasoning coherence, and function call precision. The SRML approach dynamically balances the contribution of reasoning processes and function call accuracy during training, addressing the inherent trade-off between these two critical aspects. FunReason achieves performance comparable to GPT-4o while effectively mitigating catastrophic forgetting during fine-tuning. FunReason provides a comprehensive solution for enhancing LLMs' function calling capabilities by introducing a balanced training methodology and a data refinement pipeline. For code and dataset, please refer to our repository at GitHub https://github.com/BingguangHao/FunReason