# Compositional API Recommendation for Library-Oriented Code Generation

arXiv: https://arxiv.org/abs/2402.19431 · HTML: https://mlsanity.com/paper/2402.19431/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 47 references that are in the map.
- First posted on arXiv 29 Feb 2024.

## Builds on (most cited first, 19 of 19)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Making Large Language Models Better Reasoners with Step-Aware Verifier](https://mlsanity.com/paper/2206.02336/) (2022)
- [Grounded Copilot: How Programmers Interact with Code-Generating Models](https://mlsanity.com/paper/2206.15000/) (2022)
- [Learning to Mine Aligned Code and Natural Language Pairs from Stack Overflow](https://mlsanity.com/paper/1805.08949/) (2018)
- [DocPrompting: Generating Code by Retrieving the Docs](https://mlsanity.com/paper/2207.05987/) (2022)
- [Execution-Based Evaluation for Open-Domain Code Generation](https://mlsanity.com/paper/2212.10481/) (2022)
- [Coder Reviewer Reranking for Code Generation](https://mlsanity.com/paper/2211.16490/) (2022)
- [How Do In-Context Examples Affect Compositional Generalization?](https://mlsanity.com/paper/2305.04835/) (2023)
- [Deep API Learning](https://mlsanity.com/paper/1605.08535/) (2016)
- [Code Generation Tools (Almost) for Free? A Study of Few-Shot, Pre-Trained Language Models on Code](https://mlsanity.com/paper/2206.01335/) (2022)
- [Automatic Code Summarization via ChatGPT: How Far Are We?](https://mlsanity.com/paper/2305.12865/) (2023)
- [Revisiting, Benchmarking and Exploring API Recommendation: How Far Are We?](https://mlsanity.com/paper/2112.12653/) (2021)
- [RACK: Automatic API Recommendation using Crowdsourced Knowledge](https://mlsanity.com/paper/1807.02953/) (2018)
- [SWIM: Synthesizing What I Mean](https://mlsanity.com/paper/1511.08497/) (2015)
- [PyART: Python API Recommendation in Real-Time](https://mlsanity.com/paper/2102.04706/) (2021)
- [Source Code Recommender Systems: The Practitioners' Perspective](https://mlsanity.com/paper/2302.04098/) (2023)

## Built on by (most cited first, 10 of 10)

- [SoRFT: Issue Resolving with Subtask-oriented Reinforced Fine-Tuning](https://mlsanity.com/paper/2502.20127/) (2025)
- [A Study of LLMs' Preferences for Libraries and Programming Languages](https://mlsanity.com/paper/2503.17181/) (2025)
- [Model Editing for LLMs4Code: How Far are We?](https://mlsanity.com/paper/2411.06638/) (2024)
- [Towards an Understanding of Context Utilization in Code Intelligence](https://mlsanity.com/paper/2504.08734/) (2025)
- [Repository Structure-Aware Training Makes SLMs Better Issue Resolver](https://mlsanity.com/paper/2412.19031/) (2024)
- [To See is Not to Master: Teaching LLMs to Use Private Libraries for Code Generation](https://mlsanity.com/paper/2603.15159/) (2026)
- [CCCI: Code Completion with Contextual Information for Complex Data Transfer Tasks Using Large Language Models](https://mlsanity.com/paper/2503.23231/) (2025)
- [Learning from Execution: Self-Evolving Memory for Private-Library Code Generation](https://mlsanity.com/paper/2604.24222/) (2026)
- [Dehallucinating Parallel Context Extension for Retrieval-Augmented Generation](https://mlsanity.com/paper/2412.14905/) (2024)
- [Automated Network Protocol Testing with LLM Agents](https://mlsanity.com/paper/2510.13248/) (2025)

## Abstract (arXiv)

Large language models (LLMs) have achieved exceptional performance in code generation. However, the performance remains unsatisfactory in generating library-oriented code, especially for the libraries not present in the training data of LLMs. Previous work utilizes API recommendation technology to help LLMs use libraries: it retrieves APIs related to the user requirements, then leverages them as context to prompt LLMs. However, developmental requirements can be coarse-grained, requiring a combination of multiple fine-grained APIs. This granularity inconsistency makes API recommendation a challenging task. To address this, we propose CAPIR (Compositional API Recommendation), which adopts a "divide-and-conquer" strategy to recommend APIs for coarse-grained requirements. Specifically, CAPIR employs an LLM-based Decomposer to break down a coarse-grained task description into several detailed subtasks. Then, CAPIR applies an embedding-based Retriever to identify relevant APIs corresponding to each subtask. Moreover, CAPIR leverages an LLM-based Reranker to filter out redundant APIs and provides the final recommendation. To facilitate the evaluation of API recommendation methods on coarse-grained requirements, we present two challenging benchmarks, RAPID (Recommend APIs based on Documentation) and LOCG (Library-Oriented Code Generation). Experimental results on these benchmarks, demonstrate the effectiveness of CAPIR in comparison to existing baselines. Specifically, on RAPID's Torchdata-AR dataset, compared to the state-of-the-art API recommendation approach, CAPIR improves recall@5 from 18.7% to 43.2% and precision@5 from 15.5% to 37.1%. On LOCG's Torchdata-Code dataset, compared to code generation without API recommendation, CAPIR improves pass@100 from 16.0% to 28.0%.