Open-Ended Instructable Embodied Agents with Memory-Augmented Large Language Models

Gabriel Sarch, Yue Wu, Michael Tarr, Katerina Fragkiadaki

Abstract
Pre-trained and frozen LLMs can effectively map simple scene re-arrangement instructions to programs over a robot’s visuomotor functions through appropriate few-shot example prompting. To parse open-domain natural language and adapt to a user’s idiosyncratic procedures, not known during prompt engineering time, fixed prompts fall short. In this paper, we introduce HELPER, an embodied agent equipped with an external memory of language-program pairs that parses free-form human-robot dialogue into action programs through retrieval-augmented LLM prompting: relevant memories are retrieved based on the current dialogue, instruction, correction or VLM description, and used as in-context prompt examples for LLM querying. The memory is expanded during deployment to include pairs of user’s language and action plans, to assist future inferences and personalize them to the user’s language and routines. HELPER sets a new state-of-the-art in the TEACh benchmark in both Execution from Dialog History (EDH) and Trajectory from Dialogue (TfD), with 1.7x improvement over the previous SOTA for TfD. Our models, code and video results can be found in our project’s website: https://helper-agent-llm.github.io.
Anthology ID:
2023.findings-emnlp.226
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3468–3500
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.226
DOI:
10.18653/v1/2023.findings-emnlp.226
Bibkey:
Cite (ACL):
Gabriel Sarch, Yue Wu, Michael Tarr, and Katerina Fragkiadaki. 2023. Open-Ended Instructable Embodied Agents with Memory-Augmented Large Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 3468–3500, Singapore. Association for Computational Linguistics.
Cite (Informal):
Open-Ended Instructable Embodied Agents with Memory-Augmented Large Language Models (Sarch et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-2024-clasp/2023.findings-emnlp.226.pdf
PDF Search