Category

Academic

Academic · 1 min

On the Ability of Transformers to Verify Plans

arXiv:2603.19954v1 Announce Type: new Abstract: Transformers have shown inconsistent success in AI planning tasks, and theoretical understanding of when generalization should be expected has been …

Yash Sarrof, Yupei Du, Katharina Stein, Alexander Koller, Sylvie Thi\'ebaux, Michael Hahn
10 views
Academic · 1 min

Embodied Science: Closing the Discovery Loop with Agentic Embodied AI

arXiv:2603.19782v1 Announce Type: new Abstract: Artificial intelligence has demonstrated remarkable capability in predicting scientific properties, yet scientific discovery remains an inherently physical, long-horizon pursuit governed …

Xiang Zhuang, Chenyi Zhou, Kehua Feng, Zhihui Zhu, Yunfan Gao, Yijie Zhong, Yichi Zhang, Junjie Huang, Keyan Ding, Lei Bai, Haofen Wang, Qiang Zhang, Huajun Chen
7 views
Academic · 1 min

A Subgoal-driven Framework for Improving Long-Horizon LLM Agents

arXiv:2603.19685v1 Announce Type: new Abstract: Large language model (LLM)-based agents have emerged as powerful autonomous controllers for digital environments, including mobile interfaces, operating systems, and …

Taiyi Wang, Sian Gooding, Florian Hartmann, Oriana Riva, Edward Grefenstette
37 views
Academic · 1 min

HyEvo: Self-Evolving Hybrid Agentic Workflows for Efficient Reasoning

arXiv:2603.19639v1 Announce Type: new Abstract: Although agentic workflows have demonstrated strong potential for solving complex tasks, existing automated generation methods remain inefficient and underperform, as …

Beibei Xu, Yutong Ye, Chuyun Shen, Yingbo Zhou, Cheng Chen, Mingsong Chen
9 views