Octo-planner: On-device Language Model for Planner-Action Agents
Wei Chen, Zhiyuan Li, Zhen Guo, Yikang Shen

TL;DR
This paper introduces Octo-planner, an on-device planning and action framework using optimized language models, enabling efficient autonomous decision-making on resource-limited devices.
Contribution
It presents a novel on-device framework with fine-tuned models and multi-LoRA training for multi-domain planning, improving efficiency and flexibility.
Findings
Achieved 97% success rate in in-domain tests.
Developed multi-LoRA training for multi-domain planning.
Enabled resource-efficient planning on edge devices.
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
- 🤗NexaAI/octopus-planningmodel· 16 dl· ♡ 2216 dl♡ 22
- 🤗NexaAI/octo-planner-2bmodel· 19 dl· ♡ 1019 dl♡ 10
- 🤗RichardErkhov/NexaAIDev_-_octopus-planning-4bitsmodel· 5 dl5 dl
- 🤗RichardErkhov/NexaAIDev_-_octopus-planning-8bitsmodel· 1 dl1 dl
- 🤗RichardErkhov/NexaAIDev_-_octopus-planning-awqmodel· 2 dl2 dl
- 🤗RichardErkhov/NexaAIDev_-_octo-planner-2b-8bitsmodel
- 🤗RichardErkhov/NexaAIDev_-_octo-planner-2b-awqmodel
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMulti-Agent Systems and Negotiation · Semantic Web and Ontologies · AI-based Problem Solving and Planning
MethodsAttention Is All You Need · Softmax · Layer Normalization · Absolute Position Encodings · Byte Pair Encoding · Label Smoothing · Position-Wise Feed-Forward Layer · Dropout · Adam · Linear Layer
