# ToolCoder: Teach Code Generation Models to use API search tools

arXiv: https://arxiv.org/abs/2305.04032 · HTML: https://mlsanity.com/paper/2305.04032/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 May 2023.

## Built on by (most cited first, 30 of 37)

- [Retrieval-Augmented Generation for AI-Generated Content: A Survey](https://mlsanity.com/paper/2402.19473/) (2024)
- [CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution](https://mlsanity.com/paper/2401.03065/) (2024)
- [Tool Learning with Large Language Models: A Survey](https://mlsanity.com/paper/2405.17935/) (2024)
- [Large Language Model Agent: A Survey on Methodology, Applications and Challenges](https://mlsanity.com/paper/2503.21460/) (2025)
- [Large Language Model-Based Agents for Software Engineering: A Survey](https://mlsanity.com/paper/2409.02977/) (2024)
- [Agents in Software Engineering: Survey, Landscape, and Vision](https://mlsanity.com/paper/2409.09030/) (2024)
- [What Are Tools Anyway? A Survey from the Language Model Perspective](https://mlsanity.com/paper/2403.15452/) (2024)
- [Code as Agent Harness](https://mlsanity.com/paper/2605.18747/) (2026)
- [SciReplicate-Bench: Benchmarking LLMs in Agent-driven Algorithmic Reproduction from Research Papers](https://mlsanity.com/paper/2504.00255/) (2025)
- [CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and Generation](https://mlsanity.com/paper/2311.08588/) (2023)
- [Repo2Run: Automated Building Executable Environment for Code Repository at Scale](https://mlsanity.com/paper/2502.13681/) (2025)
- [Octopus: On-device language model for function calling of software APIs](https://mlsanity.com/paper/2404.01549/) (2024)
- [Evaluation of LLMs on Syntax-Aware Code Fill-in-the-Middle Tasks](https://mlsanity.com/paper/2403.04814/) (2024)
- [GitTaskBench: A Benchmark for Code Agents Solving Real-World Tasks Through Code Repository Leveraging](https://mlsanity.com/paper/2508.18993/) (2025)
- [An LLM Agent for Automatic Geospatial Data Analysis](https://mlsanity.com/paper/2410.18792/) (2024)
- [CodeUpdateArena: Benchmarking Knowledge Editing on API Updates](https://mlsanity.com/paper/2407.06249/) (2024)
- [A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications](https://mlsanity.com/paper/2605.07358/) (2026)
- [Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression](https://mlsanity.com/paper/2505.19433/) (2025)
- [Vision2Web: A Hierarchical Benchmark for Visual Website Development with Agent Verification](https://mlsanity.com/paper/2603.26648/) (2026)
- [AskToAct: Enhancing LLMs Tool Use via Self-Correcting Clarification](https://mlsanity.com/paper/2503.01940/) (2025)
- [RGD: Multi-LLM Based Agent Debugger via Refinement and Generation Guidance](https://mlsanity.com/paper/2410.01242/) (2024)
- [Hallucination by Code Generation LLMs: Taxonomy, Benchmarks, Mitigation, and Challenges](https://mlsanity.com/paper/2504.20799/) (2025)
- [Preference-Guided Refactored Tuning for Retrieval Augmented Code Generation](https://mlsanity.com/paper/2409.15895/) (2024)
- [Towards an Understanding of Context Utilization in Code Intelligence](https://mlsanity.com/paper/2504.08734/) (2025)
- [LLM-Based Agentic Systems for Software Engineering: Challenges and Opportunities](https://mlsanity.com/paper/2601.09822/) (2026)
- [Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application](https://mlsanity.com/paper/2606.12191/) (2026)
- [CodeVisionary: An Agent-based Framework for Evaluating Large Language Models in Code Generation](https://mlsanity.com/paper/2504.13472/) (2025)
- [API Pack: A Massive Multi-Programming Language Dataset for API Call Generation](https://mlsanity.com/paper/2402.09615/) (2024)
- [GraphChain: Large Language Models for Large-scale Graph Analysis via Tool Chaining](https://mlsanity.com/paper/2511.00457/) (2025)
- [VulInstruct: Teaching LLMs Root-Cause Reasoning for Vulnerability Detection via Security Specifications](https://mlsanity.com/paper/2511.04014/) (2025)

## Abstract (arXiv)

Automatically generating source code from natural language descriptions has been a growing field of research in recent years. However, current large-scale code generation models often encounter difficulties when selecting appropriate APIs for specific contexts. These models may generate APIs that do not meet requirements or refer to non-existent APIs in third-party libraries, especially for lesser-known or private libraries. Inspired by the process of human developers using tools to search APIs, we propose ToolCoder, a novel approach that integrates API search tools with existing models to assist in code generation and API selection. To teach our model to use tools, we introduce an automated data annotation method using ChatGPT to add tool usage information into the source code data and fine-tune code generation models. During inference, we integrate API search tools into the generation process so that our model can automatically use the search tool to get suggestions when selecting an API. Our experimental results demonstrate that ToolCoder exhibits excellent performance and generalization across five public and private library code generation benchmarks, with at least 6.21% improvement on average pass@1 metrics and 9.64% improvement on average pass@10 metrics compared to state-of-the-art methods. Furthermore, we show that our relatively small ToolCoder model is comparable to one of the current best models, GPT-3.5, highlighting the potential of incorporating programming tools into the code generation process.