RIA is a closed-loop system where an LLM reasons about actions, a world model imagines outcomes via rollouts, and a safety scorer selects the best action, demonstrated in CARLA with 80.05% route completion and low collision rate.
Drivegpt4-v2: Harnessing large language model capabilities for enhanced closed-loop autonomous driving,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Reason--Imagine--Act: Closed-Loop LLM Decision Making with World Models for Autonomous Driving
RIA is a closed-loop system where an LLM reasons about actions, a world model imagines outcomes via rollouts, and a safety scorer selects the best action, demonstrated in CARLA with 80.05% route completion and low collision rate.