# ExploraCoder: Advancing code generation for multiple unseen APIs via planning and chained exploration

arXiv: https://arxiv.org/abs/2412.05366 · HTML: https://mlsanity.com/paper/2412.05366/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Dec 2024.

## Built on by (most cited first, 11 of 11)

- [Calibrate-Then-Act: Cost-Aware Exploration in LLM Agents](https://mlsanity.com/paper/2602.16699/) (2026)
- [Verification-Aware Planning for Multi-Agent Systems](https://mlsanity.com/paper/2510.17109/) (2025)
- [To See is Not to Master: Teaching LLMs to Use Private Libraries for Code Generation](https://mlsanity.com/paper/2603.15159/) (2026)
- [Learning from Execution: Self-Evolving Memory for Private-Library Code Generation](https://mlsanity.com/paper/2604.24222/) (2026)
- [Library Hallucinations in LLM-Generated Code: A Risk Analysis Grounded in Developer Queries](https://mlsanity.com/paper/2509.22202/) (2025)
- [Knowledge-Graph-Driven Data Synthesis for Low-Resource Software Development: A HarmonyOS Case Study](https://mlsanity.com/paper/2512.00380/) (2025)
- [A Study of Library Usage in Agent-Authored Pull Requests](https://mlsanity.com/paper/2512.11589/) (2025)
- [Bridging the Knowledge Void: Inference-time Acquisition of Unfamiliar Programming Languages for Coding Tasks](https://mlsanity.com/paper/2602.06976/) (2026)
- [CodeGlance: Understanding Code Reasoning Challenges in LLMs through Multi-Dimensional Feature Analysis](https://mlsanity.com/paper/2602.13962/) (2026)
- [Unseen-Codebases-Domain Data Synthesis and Training Based on Code Graphs](https://mlsanity.com/paper/2602.20799/) (2026)
- [Toward Interactive Understanding of Code APIs](https://mlsanity.com/paper/2609.32081/) (2026)

## Abstract (arXiv)

Large language models face intrinsic limitations in coding with APIs that are unseen in their training corpora. As libraries continuously evolve, it becomes impractical to exhaustively retrain LLMs with new API knowledge. This limitation hampers LLMs from solving programming problems which require newly introduced or privately maintained libraries. Inspired by exploratory programming paradigm in human behavior, we propose ExploraCoder, a training-free framework that empowers LLMs to invoke multiple unseen APIs in code solution by (1) planning a complex problem into several API invocation subtasks, and (2) experimenting with correct API usage at intermediate steps through a novel chain-of-API-exploration. We conduct evaluation on program synthesizing tasks involving complex API interactions. Experimental results demonstrate that ExploraCoder significantly improves performance for models lacking prior API knowledge, achieving absolute increases of up to 11.99% over retrieval-based approaches and 17.28% over pretraining-based methods in pass@10.