# ADC: Enhancing Function Calling Via Adversarial Datasets and Code Line-Level Feedback

arXiv: https://arxiv.org/abs/2412.17754 · HTML: https://mlsanity.com/paper/2412.17754/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Tool learning and function calling, one of 16 directions in LLM agents and tool use.
- Builds on 14 of its 23 references that are in the map.
- First posted on arXiv 23 Dec 2024.

## 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, 14 of 14)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [WizardCoder: Empowering Code Large Language Models with Evol-Instruct](https://mlsanity.com/paper/2306.08568/) (2023)
- [CodeNet: A Large-Scale AI for Code Dataset for Learning a Diversity of Coding Tasks](https://mlsanity.com/paper/2105.12655/) (2021)
- [APIGen: Automated Pipeline for Generating Verifiable and Diverse Function-Calling Datasets](https://mlsanity.com/paper/2406.18518/) (2024)
- [StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models](https://mlsanity.com/paper/2403.07714/) (2024)
- [xLAM: A Family of Large Action Models to Empower AI Agent Systems](https://mlsanity.com/paper/2409.03215/) (2024)
- [Granite-Function Calling Model: Introducing Function Calling Abilities via Multi-task Learning of Granular Tasks](https://mlsanity.com/paper/2407.00121/) (2024)
- [WaveCoder: Widespread And Versatile Enhancement For Code Large Language Models By Instruction Tuning](https://mlsanity.com/paper/2312.14187/) (2023)
- [mABC: multi-Agent Blockchain-Inspired Collaboration for root cause analysis in micro-services architecture](https://mlsanity.com/paper/2404.12135/) (2024)
- [Efficient and Scalable Estimation of Tool Representations in Vector Space](https://mlsanity.com/paper/2409.02141/) (2024)
- [Lemur: Log Parsing with Entropy Sampling and Chain-of-Thought Merging](https://mlsanity.com/paper/2402.18205/) (2024)
- [ECLIPSE: Semantic Entropy-LCS for Cross-Lingual Industrial Log Parsing](https://mlsanity.com/paper/2405.13548/) (2024)

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

- [TTPA: Token-level Tool-use Preference Alignment Training Framework with Fine-grained Evaluation](https://mlsanity.com/paper/2505.20016/) (2025)
- [Close the Loop: Synthesizing Infinite Tool-Use Data via Multi-Agent Role-Playing](https://mlsanity.com/paper/2512.23611/) (2025)
- [Knowledge-Graph-Driven Data Synthesis for Low-Resource Software Development: A HarmonyOS Case Study](https://mlsanity.com/paper/2512.00380/) (2025)
- [M2G-Eval: Enhancing and Evaluating Multi-granularity Multilingual Code Generation](https://mlsanity.com/paper/2512.22628/) (2025)
- [Exploring Weaknesses in Function Call Models via Reinforcement Learning: An Adversarial Data Augmentation Approach](https://mlsanity.com/paper/2601.19122/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have made significant strides in Natural Language Processing and coding, yet they struggle with robustness and accuracy in complex function calls. To tackle these challenges, this paper introduces ADC, an innovative approach that enhances LLMs' ability to follow function formats and match complex parameters. ADC utilizes a high-quality code fine-tuning dataset with line-level execution feedback, providing granular process supervision that fosters strong logical reasoning and adherence to function formats. It also employs an adversarial dataset generation process to improve parameter matching. The staged training methodology capitalizes on both enriched code datasets and refined adversarial datasets, leading to marked improvements in function calling capabilities on the Berkeley Function-Calling Leaderboard (BFCL) Benchmark. The innovation of ADC lies in its strategic combination of process supervision, adversarial refinement, and incremental learning, setting a new standard for LLM proficiency in complex function calling.