mlsanityData to 7 Oct 2026

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

arXiv 2412.17754 ↗First posted 23 Dec 2024cs.SEcited by 5

On the map: LLM agents and tool use → Tool learning and function calling

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.

Key facts. Cited by 5 papers in the map (data through 7 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.

Builds on

14 of 23 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Efficient and Scalable Estimation of Tool Representations in Vector Space2 Sep
  2. 2024Granite-Function Calling Model: Introducing Function Calling Abilities via Multi-task Learning of Granular Tasks27 Jun
  3. 2024APIGen: Automated Pipeline for Generating Verifiable and Diverse Function-Calling Datasets26 Jun
  4. 2024StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models12 Mar

Other references · 10

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  4. 2023WizardCoder: Empowering Code Large Language Models with Evol-Instructcited by 728
  5. 2021CodeNet: A Large-Scale AI for Code Dataset for Learning a Diversity of Coding Taskscited by 199
  6. 2024xLAM: A Family of Large Action Models to Empower AI Agent Systemscited by 108
  7. 2023WaveCoder: Widespread And Versatile Enhancement For Code Large Language Models By Instruction Tuningcited by 42
  8. 2024mABC: multi-Agent Blockchain-Inspired Collaboration for root cause analysis in micro-services architecturecited by 26
  9. 2024Lemur: Log Parsing with Entropy Sampling and Chain-of-Thought Mergingcited by 16
  10. 2024ECLIPSE: Semantic Entropy-LCS for Cross-Lingual Industrial Log Parsingcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 4; 2026: 1.

5 papers.

  1. 2025TTPA: Token-level Tool-use Preference Alignment Training Framework with Fine-grained Evaluationcited by 9
  2. 2025Close the Loop: Synthesizing Infinite Tool-Use Data via Multi-Agent Role-Playingcited by 9
  3. 2025Knowledge-Graph-Driven Data Synthesis for Low-Resource Software Development: A HarmonyOS Case Studycited by 1
  4. 2025M2G-Eval: Enhancing and Evaluating Multi-granularity Multilingual Code Generationcited by 1
  5. 2026Exploring Weaknesses in Function Call Models via Reinforcement Learning: An Adversarial Data Augmentation Approachcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025AKD : Adversarial Knowledge Distillation For Large Language Models Alignment on Coding tasks
  2. 2025Watch your steps: Dormant Adversarial Behaviors that Activate upon LLM Finetuning
  3. 2026ACE: Self-Evolving LLM Coding Framework via Adversarial Unit Test Generation and Preference Optimization
  4. 2025AR2: Adversarial Reinforcement Learning for Abstract Reasoning in Large Language Models
  5. 2024Efficient Adversarial Training in LLMs with Continuous Attacks
  6. 2024Large Language Models as Robust Data Generators in Software Analytics: Are We There Yet?
  7. 2025Chain-of-Code Collapse: Reasoning Failures in LLMs via Adversarial Prompting in Code Generation
  8. 2024Improving Small-Scale Large Language Models Function Calling for Reasoning Tasks