CommandSwarm uses LoRA-adapted LLMs with safety filtering and deterministic parsing to generate valid behavior trees from text or speech, raising zero-shot BLEU to 0.663 and syntactic validity to 72% on synthetic swarm scenarios.
A survey of behavior trees in robotics and ai
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.RO 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
CommandSwarm: Safety-Aware Natural Language-to-Behavior-Tree Generation for Robotic Swarms
CommandSwarm uses LoRA-adapted LLMs with safety filtering and deterministic parsing to generate valid behavior trees from text or speech, raising zero-shot BLEU to 0.663 and syntactic validity to 72% on synthetic swarm scenarios.