作者位次 #3/9ACL 2026Poster· Natural Language Processing
Model-Based Imaginative Planning for Embodied Agents
Junru Song · Hengzhe Jin · Yucong Huang · Tingsong Jiang · Weien Zhou · Feifei Wang · Yang Yang · Ying Wen · Wen Yao
摘要
Reasoning and planning critically rely on a predictive dynamics model. In symbolic domains such as mathematics and code, large language models (LLMs) internalize transition rules during pretraining, allowing reinforcement learning or test-time scaling to effectively elicit and generalize their re...