# Octopus v3: Technical Report for On-device Sub-billion Multimodal AI Agent

arXiv: https://arxiv.org/abs/2404.11459 · HTML: https://mlsanity.com/paper/2404.11459/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 35 of its 54 references that are in the map.
- First posted on arXiv 17 Apr 2024.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 30 of 35)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [AI2-THOR: An Interactive 3D Environment for Visual AI](https://mlsanity.com/paper/1712.05474/) (2017)
- [ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks](https://mlsanity.com/paper/1912.01734/) (2019)
- [A Survey on Visual Transformer](https://mlsanity.com/paper/2012.12556/) (2020)
- [Multimodal Transformer for Unaligned Multimodal Language Sequences](https://mlsanity.com/paper/1906.00295/) (2019)
- [A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects](https://mlsanity.com/paper/2004.02806/) (2020)
- [Embodied Question Answering](https://mlsanity.com/paper/1711.11543/) (2017)
- [Learning to Explore using Active Neural SLAM](https://mlsanity.com/paper/2004.05155/) (2020)
- [Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception](https://mlsanity.com/paper/2401.16158/) (2024)
- [A Survey on Multimodal Large Language Models for Autonomous Driving](https://mlsanity.com/paper/2311.12320/) (2023)
- [MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases](https://mlsanity.com/paper/2402.14905/) (2024)
- [A Study of Generative Large Language Model for Medical Research and Healthcare](https://mlsanity.com/paper/2305.13523/) (2023)
- [Drive Like a Human: Rethinking Autonomous Driving with Large Language Models](https://mlsanity.com/paper/2307.07162/) (2023)
- [Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAE](https://mlsanity.com/paper/2103.10022/) (2021)

## Built on by (most cited first, 7 of 7)

- [Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaboration](https://mlsanity.com/paper/2406.01014/) (2024)
- [Large Language Model-Brained GUI Agents: A Survey](https://mlsanity.com/paper/2411.18279/) (2024)
- [On-Device Language Models: A Comprehensive Review](https://mlsanity.com/paper/2409.00088/) (2024)
- [AutoNeural: Co-Designing Vision-Language Models for NPU Inference](https://mlsanity.com/paper/2512.02924/) (2025)
- [Octopus v4: Graph of language models](https://mlsanity.com/paper/2404.19296/) (2024)
- [Towards Pervasive Distributed Agentic Generative AI -- A State of The Art](https://mlsanity.com/paper/2506.13324/) (2025)
- [A Systematic Evaluation of On-Device LLMs: Quantization, Performance, and Resources](https://mlsanity.com/paper/2505.15030/) (2025)

## Abstract (arXiv)

A multimodal AI agent is characterized by its ability to process and learn from various types of data, including natural language, visual, and audio inputs, to inform its actions. Despite advancements in large language models that incorporate visual data, such as GPT-4V, effectively translating image-based data into actionable outcomes for AI agents continues to be challenging. In this paper, we introduce a multimodal model that incorporates the concept of functional token specifically designed for AI agent applications. To ensure compatibility with edge devices, our model is optimized to a compact size of less than 1B parameters. Like GPT-4, our model can process both English and Chinese. We demonstrate that this model is capable of operating efficiently on a wide range of edge devices, including as constrained as a Raspberry Pi.