Scale-Plan: Scalable Language-Enabled Task Planning for Heterogeneous Multi-Robot Teams
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918380641976320 |
|---|---|
| author | Gupta, Piyush Bae, Sangjae Li, Jiachen Isele, David |
| author_facet | Gupta, Piyush Bae, Sangjae Li, Jiachen Isele, David |
| contents | Long-horizon task planning for heterogeneous multi-robot systems is essential for deploying collaborative teams in real-world environments; yet, it remains challenging due to the large volume of perceptual information, much of which is irrelevant to task objectives and burdens planning. Traditional symbolic planners rely on manually constructed problem specifications, limiting scalability and adaptability, while recent large language model (LLM)-based approaches often suffer from hallucinations and weak grounding-i.e., poor alignment between generated plans and actual environmental objects and constraints-in object-rich settings. We present Scale-Plan, a scalable LLM-assisted framework that generates compact, task-relevant problem representations from natural language instructions. Given a PDDL domain specification, Scale-Plan constructs an action graph capturing domain structure and uses shallow LLM reasoning to guide a structured graph search that identifies a minimal subset of relevant actions and objects. By filtering irrelevant information prior to planning, Scale-Plan enables efficient decomposition, allocation, and long-horizon plan generation. We evaluate our approach on complex multi-agent tasks and introduce MAT2-THOR, a cleaned benchmark built on AI2-THOR for reliable evaluation of multi-robot planning systems. Scale-Plan outperforms pure LLM and hybrid LLM-PDDL baselines across all metrics, improving scalability and reliability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_08814 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Scale-Plan: Scalable Language-Enabled Task Planning for Heterogeneous Multi-Robot Teams Gupta, Piyush Bae, Sangjae Li, Jiachen Isele, David Robotics Artificial Intelligence Emerging Technologies Multiagent Systems Long-horizon task planning for heterogeneous multi-robot systems is essential for deploying collaborative teams in real-world environments; yet, it remains challenging due to the large volume of perceptual information, much of which is irrelevant to task objectives and burdens planning. Traditional symbolic planners rely on manually constructed problem specifications, limiting scalability and adaptability, while recent large language model (LLM)-based approaches often suffer from hallucinations and weak grounding-i.e., poor alignment between generated plans and actual environmental objects and constraints-in object-rich settings. We present Scale-Plan, a scalable LLM-assisted framework that generates compact, task-relevant problem representations from natural language instructions. Given a PDDL domain specification, Scale-Plan constructs an action graph capturing domain structure and uses shallow LLM reasoning to guide a structured graph search that identifies a minimal subset of relevant actions and objects. By filtering irrelevant information prior to planning, Scale-Plan enables efficient decomposition, allocation, and long-horizon plan generation. We evaluate our approach on complex multi-agent tasks and introduce MAT2-THOR, a cleaned benchmark built on AI2-THOR for reliable evaluation of multi-robot planning systems. Scale-Plan outperforms pure LLM and hybrid LLM-PDDL baselines across all metrics, improving scalability and reliability. |
| title | Scale-Plan: Scalable Language-Enabled Task Planning for Heterogeneous Multi-Robot Teams |
| topic | Robotics Artificial Intelligence Emerging Technologies Multiagent Systems |
| url | https://arxiv.org/abs/2603.08814 |