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.
Webvoyager: Building an end-to-end web agent with large multimodal models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
ProjGuard monitors agent trajectories with low-dimensional projections to cut unsafe actions from 16% to 3% and raise task completion from 59% to 65% on OS-Harm.
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.
-
ProjGuard: Safety Monitoring for Computer-Use Agents via Low-Dimensional Projections
ProjGuard monitors agent trajectories with low-dimensional projections to cut unsafe actions from 16% to 3% and raise task completion from 59% to 65% on OS-Harm.