DriveFuture achieves SOTA results on NAVSIM by conditioning latent world model states on future predictions to directly inform trajectory planning.
Adawm: Adaptive world model based planning for autonomous driving
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 3polarities
background 3representative citing papers
The paper introduces a unified framework for world models that fully incorporates all cognitive functions from Cognitive Architecture Theory, highlights under-researched areas in motivation and meta-cognition, and proposes Epistemic World Models as a new category for scientific discovery agents.
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.
The survey structures agentic reasoning for LLMs into foundational, self-evolving, and collective multi-agent layers while distinguishing in-context orchestration from post-training optimization and reviewing applications across domains.
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.
-
Agentic Reasoning for Large Language Models
The survey structures agentic reasoning for LLMs into foundational, self-evolving, and collective multi-agent layers while distinguishing in-context orchestration from post-training optimization and reviewing applications across domains.