Octo-planner: On-device Language Model for Planner-Action Agents
3.80T1 sourcearXiv cs.HC
arXiv cs.HCoriginal source ↗
Source record
Published by arXiv cs.HC (T1 source). The original is at https://arxiv.org/abs/2406.18082.
Pipeline notes
The summary and note below are generated by the signal pipeline — they are Beyond Desk’s reading, not quotations from the source.
SummaryPaper presents Octo-planner, a two-component on-device agent framework using a fine-tuned Phi-3 Mini (3.8B) as planner and Octopus model for action execution. Uses multi-LoRA weight merging to handle multi-domain queries, reports 97% success in in-domain tests, and releases model weights open-source.
Why it mattersConcrete on-device planner-action architecture with open weights, a multi-LoRA merging recipe, and reproducible success rate — useful reference for deploying local agent stacks.
Cited by
No citations on record.