Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.00797 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911295016534016 |
|---|---|
| author | Sun, Nan Mao, Bo Li, Yongchang Wang, Chenxu Guo, Di Liu, Huaping |
| author_facet | Sun, Nan Mao, Bo Li, Yongchang Wang, Chenxu Guo, Di Liu, Huaping |
| contents | Foundation models have become central to unifying perception and planning in robotics, yet real-world deployment exposes a mismatch between their monolithic assumption that a single model can handle all cognitive functions and the distributed, dynamic nature of practical service workflows. Vision-language models offer strong semantic understanding but lack embodiment-aware action capabilities while relying on hand-crafted skills. Vision-Language-Action policies enable reactive manipulation but remain brittle across embodiments, weak in geometric grounding, and devoid of proactive collaboration mechanisms. These limitations indicate that scaling a single model alone cannot deliver reliable autonomy for service robots operating in human-populated settings. To address this gap, we present InteractGen, an LLM-powered multi-agent framework that decomposes robot intelligence into specialized agents for continuous perception, dependency-aware planning, decision and verification, failure reflection, and dynamic human delegation, treating foundation models as regulated components within a closed-loop collective. Deployed on a heterogeneous robot team and evaluated in a three-month open-use study, InteractGen improves task success, adaptability, and human-robot collaboration, providing evidence that multi-agent orchestration offers a more feasible path toward socially grounded service autonomy than further scaling standalone models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_00797 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Transforming Monolithic Foundation Models into Embodied Multi-Agent Architectures for Human-Robot Collaboration Sun, Nan Mao, Bo Li, Yongchang Wang, Chenxu Guo, Di Liu, Huaping Robotics Foundation models have become central to unifying perception and planning in robotics, yet real-world deployment exposes a mismatch between their monolithic assumption that a single model can handle all cognitive functions and the distributed, dynamic nature of practical service workflows. Vision-language models offer strong semantic understanding but lack embodiment-aware action capabilities while relying on hand-crafted skills. Vision-Language-Action policies enable reactive manipulation but remain brittle across embodiments, weak in geometric grounding, and devoid of proactive collaboration mechanisms. These limitations indicate that scaling a single model alone cannot deliver reliable autonomy for service robots operating in human-populated settings. To address this gap, we present InteractGen, an LLM-powered multi-agent framework that decomposes robot intelligence into specialized agents for continuous perception, dependency-aware planning, decision and verification, failure reflection, and dynamic human delegation, treating foundation models as regulated components within a closed-loop collective. Deployed on a heterogeneous robot team and evaluated in a three-month open-use study, InteractGen improves task success, adaptability, and human-robot collaboration, providing evidence that multi-agent orchestration offers a more feasible path toward socially grounded service autonomy than further scaling standalone models. |
| title | Transforming Monolithic Foundation Models into Embodied Multi-Agent Architectures for Human-Robot Collaboration |
| topic | Robotics |
| url | https://arxiv.org/abs/2512.00797 |