SiRA uses LLM world models for simulative reasoning to achieve up to 124% higher task completion and 32.2% navigation success versus reactive baselines in web environments.
Owl: Optimized workforce learning for general multi-agent assistance in real-world task automation, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
General Agentic Planning Through Simulative Reasoning with World Models
SiRA uses LLM world models for simulative reasoning to achieve up to 124% higher task completion and 32.2% navigation success versus reactive baselines in web environments.