Debate2Create: Robot Co-design via Multi-Agent LLM Debate
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918350050820096 |
|---|---|
| author | Qiu, Kevin Cygan, Marek |
| author_facet | Qiu, Kevin Cygan, Marek |
| contents | We introduce Debate2Create (D2C), a multi-agent LLM framework that formulates robot co-design as structured, iterative debate grounded in physics-based evaluation. A design agent and control agent engage in a thesis-antithesis-synthesis loop, while pluralistic LLM judges provide multi-objective feedback to steer exploration. Across five MuJoCo locomotion benchmarks, D2C achieves up to $3.2\times$ the default Ant score and $\sim9\times$ on Swimmer, outperforming prior LLM-based methods and black-box optimization. Iterative debate yields 18--35% gains over compute-matched zero-shot generation, and D2C-generated rewards transfer to default morphologies in 4/5 tasks. Our results demonstrate that structured multi-agent debate offers an effective alternative to hand-designed objectives for joint morphology-reward optimization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_25850 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Debate2Create: Robot Co-design via Multi-Agent LLM Debate Qiu, Kevin Cygan, Marek Robotics Machine Learning Multiagent Systems We introduce Debate2Create (D2C), a multi-agent LLM framework that formulates robot co-design as structured, iterative debate grounded in physics-based evaluation. A design agent and control agent engage in a thesis-antithesis-synthesis loop, while pluralistic LLM judges provide multi-objective feedback to steer exploration. Across five MuJoCo locomotion benchmarks, D2C achieves up to $3.2\times$ the default Ant score and $\sim9\times$ on Swimmer, outperforming prior LLM-based methods and black-box optimization. Iterative debate yields 18--35% gains over compute-matched zero-shot generation, and D2C-generated rewards transfer to default morphologies in 4/5 tasks. Our results demonstrate that structured multi-agent debate offers an effective alternative to hand-designed objectives for joint morphology-reward optimization. |
| title | Debate2Create: Robot Co-design via Multi-Agent LLM Debate |
| topic | Robotics Machine Learning Multiagent Systems |
| url | https://arxiv.org/abs/2510.25850 |