STaLM warm-starts a hybrid-action Monte Carlo tree search with task plans generated by a single LLM query, outperforming pure search and prior LLM planners on six geometric task and motion planning problems.
In: The Conference on Lifelong Learning Agents, Pisa, Italy, 29-1 August
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Prime the search: Using large language models for guiding geometric task and motion planning by warm-starting tree search
STaLM warm-starts a hybrid-action Monte Carlo tree search with task plans generated by a single LLM query, outperforming pure search and prior LLM planners on six geometric task and motion planning problems.