activity
20242026
most citedExpanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling

16 citations · 16 across the 4 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

Glasseek: A Transparent Recipe for Training and Trustworthy Evaluation of DeepSearch Agents

Cong Pang, Jiaqi Su, Chengrui Wu +13

Deep search enables language agents to solve complex information-seeking tasks through iterative web exploration. However, developing robust open-source agents remains challenging…