The work is under review at NeurIPS 2026.

I am the co-first author of this paper, collaborating with Dongsheng Hou, Yuhan Rui, Zhen Cao, Yepang Liu$^\dagger$ from SUSTech.

The paper have been submitted to the conference of NeurIPS 2026 (Contribution: Concept&Feasibility).

I am currently working on a research paper in the field of Reinforcement learning, specifically focusing on dealing with sparse reward problems in reinforcement learning.

I am the co-first author of this paper, collaborating with Dongsheng Hou, Yuhan Rui from SUSTech.

We are aimed to publish our research findings in AAAI 2027.