Graph-Conditioned On-Policy Agent Distillation is introduced, which enriches an off-the-shelf teacher's scoring context with execution evidence, and indexes repeated teacher executions by shared states while preserving complete successful and failed histories.
Xiao-Han Yi, Wen Luo, Ya-Ni Huang et al.· 1 citation
AdvRole is proposed, an adversarial context rewriting framework that turns role-playing RL into a closed-loop curriculum and shows that AdvRole consistently outperforms baselines.
This framework surveys manipulation, navigation, locomotion, autonomous driving, and general embodied learning, tracing technical progressions, clarifying capability requirements, and examining datasets, benchmarks, and evaluation protocols.
CaM-Wolf is introduced, the first SDG agent that integrates multimodal perception and generation and achieves superior agent gameplay performance and enhances the quality of human-AI interaction.
Zheng Zhang, Nan-Jie Yao, Jia-Ru He et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.