Hi! Thank you for this comprehensive collection of agentic reasoning works.
I would like to suggest adding a paper that explores reasoning and planning for multimodal agents (specifically in video browsing tasks).
Title: Video-Browser: Towards Agentic Open-web Video Browsing Link: https://arxiv.org/abs/2512.23044 Code: https://github.com/chrisx599/Video-Browser
We introduces a benchmark and an agent architecture that focuses on efficiently retrieve open-web information from videos, which aligns with the "Agentic Reasoning" theme of this repo.
Thanks for considering!