Firehose

Filtered to Papers, tagged “graph world models” · clear filters

Browse: People · Companies · Papers · Podcasts · Hacker News · Deep dives

All People Companies Papers Podcasts Hacker News

Browse by tag

continual learning 28 reinforcement learning 12 robotics 4 vision-language models 4 benchmarking 3 computer vision 3 embodied AI 3 language models 3 large language models 3 on-policy distillation 3 video generation 3

16 SEP 2026 · Paper

GAVEL: Graph World Models for Verified and Efficient Long-Horizon LLM Task Planning

This paper develops a framework called GAVEL that helps long-horizon language models (LLMs) plan tasks for robots more effectively by predicting and repairing potential errors. Practitioners caring about reliable and efficient robot planning might find this approach useful.

graph world models continual learning robot planning embodied AI LLMs