SAGE: Training Smart Any-Horizon Agents for Long Video Reasoning with Reinforcement Learning,

Jain, J; Li, J; Ma, Z; Zhang, J; Kim, C; Lee, S; Tripathi, R; Gupta, T; Clark, C; Shi, H

skip to main content

An official website of the United States government Here's how you know

Official websites use .gov

A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS

A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Attention:

The NSF Public Access Repository (PAR) system and access will be unavailable from 5:00 PM ET until 8:00 PM ET on Friday, September 11 due to maintenance. We apologize for the inconvenience.

Citation Details

This content will become publicly available on June 3, 2027

SAGE: Training Smart Any-Horizon Agents for Long Video Reasoning with Reinforcement Learning,

Award ID(s):: 2427478

PAR ID:: 10694450

Author(s) / Creator(s):: Jain, J; Li, J; Ma, Z; Zhang, J; Kim, C; Lee, S; Tripathi, R; Gupta, T; Clark, C; Shi, H

Publisher / Repository:: IEEE Conference on Computer Vision and Pattern Recognition, 2026

Date Published:: 2026-06-03

Format(s):: Medium: X

Sponsoring Org:: National Science Foundation

Free Publicly Accessible Full Text
This content will become publicly available on June 3, 2027
Conference Proceeding:
The DOI is not currently available.

More Like this