---
title: "HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face"
license: CC-BY-4.0
license_url: https://creativecommons.org/licenses/by/4.0/
license_note: 'paper is arXiv non-exclusive distribution license (verified on arXiv abs page 2026-11-12); this pointer note is our own words and is CC BY 4.0; we link to the paper rather than reproduce it'
source: https://iinventedlight.com/library/notes/2303-17580-hugginggpt.md
source_license: "arXiv non-exclusive distribution license"
attribution: 'Pointer by iinventedlight (AI-assisted). Source: Yongliang Shen, Kaitao Song, Xu Tan, Dongsheng Li, Weiming Lu, Yueting Zhuang, HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face (arXiv non-exclusive distribution license). This note links to the paper rather than reproducing it.'
author: 'iinventedlight (AI-assisted)'
date: 2026-11-12
status: published
approved_by: "Cole Withington, 2026-11-12 14:44 PT, Librarian chat widget t51s316: \"Yes, publish all 100 second-list arXiv notes\""
checked_on: 2026-11-12
as_of: 2026-11-12
confidence: medium
untested: 'Pointer note only. Paper not reproduced. Abs page and license checked 2026-11-12.'
category: arxiv
topic_area: 'ai-research: agents'
tags: arxiv, agents, tools, hugging-face, orchestration
arxiv_id: 2303.17580
alias: 2303-17580-hugginggpt
type: pointer
format: pointer
sources:
  - id: S1
    title: "HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face"
    publisher: arXiv
    authors: "Yongliang Shen, Kaitao Song, Xu Tan, Dongsheng Li, Weiming Lu, Yueting Zhuang"
    url: https://arxiv.org/abs/2303.17580
    version_read: "v4 (3 Dec 2023)"
    accessed: 2026-11-12
    license: "arXiv non-exclusive distribution license"
---
# HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face

## Summary
[HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face](https://arxiv.org/abs/2303.17580) (2023) is an early system that uses a language model as a controller over many expert models. ChatGPT plans a request, picks models from Hugging Face by their function descriptions, runs each subtask, and then summarizes the results.

What it introduced: a pattern in which language is the interface between a general controller and a community of specialist models for language, vision, speech, and other modalities. The point is not to train one model to do every task, but to orchestrate models that already exist.

What it led to: a wave of tool-using and model-routing agents, including visual assistants that call image models from a language-model loop. Live notes: [2302-04761-toolformer](https://iinventedlight.com/library/notes/2302-04761-toolformer/) and [2305-15334-gorilla](https://iinventedlight.com/library/notes/2305-15334-gorilla/). Visual ChatGPT and API-Bank are pointer notes in this batch.

Where to read it: https://arxiv.org/abs/2303.17580 (v4, last revised 3 Dec 2023).

The paper is posted on arXiv under the arXiv non-exclusive distribution license. This note links to it rather than reproducing it. The note itself is CC BY 4.0.

License: this note is CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Pointer by iinventedlight (AI-assisted). Paper license: arXiv non-exclusive distribution; this note links to it and does not reproduce it.

---

Agents: [/agents.md](/agents.md) | [/.well-known/agent-library.json](/.well-known/agent-library.json).
