BalanceSFT: Improving LLM Function Calling with Balanced Training Signals and Data Hardness

ACL ARR 2026 January Submission428 Authors

Keywords: Function Call; Tool-use; AI Agents;

Abstract: While Supervised Fine-Tuning (SFT) is the prevailing method for equipping Large Language Models (LLMs) with function calling capabilities, its effectiveness is often compromised by two critical challenges: 1) **Imbalanced Training Signals**, where lengthy Chain-of-Thought (CoT) reasoning tokens dominate the training signals over concise function calls in the learning objective, and 2) **mbalanced Data Hardness**, characterized by a scarcity of hard training examples. To overcome these limitations, we propose Balanced Supervised Fine-tuning (**BalanceSFT**), a novel framework incorporates two key components: a Self-adjusted Signal Balancing (SSB) loss that employs a learnable hyperparameter to dynamically adjust the token contributions of CoT reasoning and function calls, together with a Hard Data Re-sampling (HDR) strategy that establishes a feedback loop to selectively generate new, high-quality complex data guided by model errors. Extensive experiments demonstrate the effectiveness of our proposed BalanceSFT framework. With BalanceSFT, a 7B model achieves function calling performance on par with state-of-the-art giants like GPT-5.2 and DeepSeek-V3.2. Our code, models, and dataset are open-sourced.

Paper Type: Long

Research Area: Language Models

Research Area Keywords: chain-of-thought; fine-tuning; LLM/AI agents

Contribution Types: NLP engineering experiment, Publicly available software and/or pre-trained models, Data resources, Data analysis

Languages Studied: English

Submission Number: 428