# Octo-planner: On-device Language Model for Planner-Action Agents

arXiv: https://arxiv.org/abs/2406.18082 · HTML: https://mlsanity.com/paper/2406.18082/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 12 of its 25 references that are in the map.
- First posted on arXiv 26 Jun 2024.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 12 of 12)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [GPT-4V(ision) is a Generalist Web Agent, if Grounded](https://mlsanity.com/paper/2401.01614/) (2024)
- [Deep Learning on a Data Diet: Finding Important Examples Early in Training](https://mlsanity.com/paper/2107.07075/) (2021)
- [TravelPlanner: A Benchmark for Real-World Planning with Language Agents](https://mlsanity.com/paper/2402.01622/) (2024)
- [LoRA+: Efficient Low Rank Adaptation of Large Models](https://mlsanity.com/paper/2402.12354/) (2024)
- [VeRA: Vector-based Random Matrix Adaptation](https://mlsanity.com/paper/2310.11454/) (2023)
- [Instruction Mining: Instruction Data Selection for Tuning Large Language Models](https://mlsanity.com/paper/2307.06290/) (2023)
- [Octopus v2: On-device language model for super agent](https://mlsanity.com/paper/2404.01744/) (2024)
- [A Survey on Security and Privacy Issues in Edge Computing-Assisted Internet of Things](https://mlsanity.com/paper/2008.03252/) (2020)

## Built on by (most cited first, 8 of 8)

- [Large Language Model-Brained GUI Agents: A Survey](https://mlsanity.com/paper/2411.18279/) (2024)
- [Foundations and Recent Trends in Multimodal Mobile Agents: A Survey](https://mlsanity.com/paper/2411.02006/) (2024)
- [Division-of-Thoughts: Harnessing Hybrid Language Model Synergy for Efficient On-Device Agents](https://mlsanity.com/paper/2502.04392/) (2025)
- [AutoNeural: Co-Designing Vision-Language Models for NPU Inference](https://mlsanity.com/paper/2512.02924/) (2025)
- [CAMPHOR: Collaborative Agents for Multi-input Planning and High-Order Reasoning On Device](https://mlsanity.com/paper/2410.09407/) (2024)
- [AgenTEE: Confidential LLM Agent Execution on Edge Devices](https://mlsanity.com/paper/2604.18231/) (2026)
- [Alopex: A Computational Framework for Enabling On-Device Function Calls with LLMs](https://mlsanity.com/paper/2411.05209/) (2024)
- [Should SLMs be in the Driver's Seat? A Study of Local Models as Interpreters in Cloud-Written Agent Programs](https://mlsanity.com/paper/2610.14209/) (2026)

## Abstract (arXiv)

AI agents have become increasingly significant in various domains, enabling autonomous decision-making and problem-solving. To function effectively, these agents require a planning process that determines the best course of action and then executes the planned actions. In this paper, we present an efficient on-device Planner-Action framework that separates planning and action execution into two distinct components: a planner agent based on Phi-3 Mini, a 3.8 billion parameter LLM optimized for edge devices, and an action agent using the Octopus model for function execution. The planner agent first responds to user queries by decomposing tasks into a sequence of sub-steps, which are then executed by the action agent. To optimize performance on resource-constrained devices, we employ model fine-tuning instead of in-context learning, reducing computational costs and energy consumption while improving response times. Our approach involves using GPT-4 to generate diverse planning queries and responses based on available functions, with subsequent validations to ensure data quality. We fine-tune the Phi-3 Mini model on this curated dataset, achieving a 97% success rate in our in-domain test environment. To address multi-domain planning challenges, we developed a multi-LoRA training method that merges weights from LoRAs trained on distinct function subsets. This approach enables flexible handling of complex, multi-domain queries while maintaining computational efficiency on resource-constrained devices. To support further research, we have open-sourced our model weights at https://huggingface.co/NexaAIDev/octopus-planning. For the demo, please refer to https://www.nexa4ai.com/octo-planner.