AI Paper Atlas

Research map / Video / Video-language understanding

Ego-R1: Agentic Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning

Shulin Tian, Rui Wang, Hongming Guo, Penghao Wu, Yuhao Dong, Xiuying Wang, Jingkang Yang, Hao Zhang, Hongyuan Zhu, Ziwei Liu

TPAMI 2026 · Video › Video-language understanding · approach: Egocentric video understanding · 65 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add SFT on CoTT data to the base model (ablation)Qwen2.5-3B-Instruct · Ego-R1 Benchaccuracy (%): 1.4 -> 34.3Improved
add RL (GRPO) on top of SFT (ablation)Ego-R1-SFT · Ego-R1 Benchaccuracy (%): 34.3 -> 46.0Improved
apply RL alone without CoTT SFT (ablation)Qwen2.5-3B-Instruct · Ego-R1 Benchaccuracy (%): 1.4 -> 0.0Hurt
apply RL alone without CoTT SFT (ablation)Qwen2.5-3B-Instruct · Ego-R1 Benchformat accuracy (%): 4.3 -> 13.3Improved
add SFT on CoTT data (ablation)Qwen2.5-3B-Instruct · Ego-R1 Benchformat accuracy (%): 4.3 -> 100.0Improved
replace LLaVA-Video with Gemini-1.5-Pro as video_llm (ablation)Ego-R1 · Ego-R1 Benchaccuracy (%): 43.7 -> 46.0Improved
add video_llm and vlm tools to RAG-only (ablation)Ego-R1 · Ego-R1 Benchaccuracy (%): 39.7 -> 46.0Improved

Later papers that compared with this method

2 later accepted papers report Ego-R1 as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy