[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]

![webagentlab Avatar](https://lunarcrush.com/gi/w:24/cr:twitter::1857262354221957120.png) WebAgentlab@ICML25 ✈️ [@webagentlab](/creator/twitter/webagentlab) on x XXX followers
Created: 2025-07-11 06:32:06 UTC

WebArXiv: Evaluating Multimodal Agents on Time-Invariant arXiv Tasks

WebArXiv is a static benchmark designed to evaluate multimodal web agents on time-invariant tasks from the arXiv platform, addressing issues of ground truth instability and proposing a dynamic reflection mechanism to enhance agent decision-making.

Zihao Sun, Meng Fang, Ling Chen

Australian Artificial Intelligence Institute; University of Liverpool



![](https://pbs.twimg.com/media/Gvjn-qgakAM_bdX.jpg)

XX engagements

![Engagements Line Chart](https://lunarcrush.com/gi/w:600/p:tweet::1943558900923748681/c:line.svg)

**Related Topics**
[artificial](/topic/artificial)
[web agents](/topic/web-agents)
[$ai4](/topic/$ai4)

[Post Link](https://x.com/webagentlab/status/1943558900923748681)