CocoaBench: Evaluating Unified Digital Agents in the Wild
Paper • 2604.11201 • Published • 24
Sun Haotian
liamth27
AI & ML interests
Open-source multimodal experiment workflows. Mostly focused on experiments.
Recent Activity
liked a model about 4 hours ago
tencent/HY-Embodied-0.5 upvoted a paper about 10 hours ago
CocoaBench: Evaluating Unified Digital Agents in the Wild liked a model 2 days ago
ViratGarg/postnorm-transformerOrganizations
None yet
upvoted a paper about 10 hours ago
upvoted 3
papers 4 days ago
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability
Paper • 2604.06628 • Published • 308
Learning to Hint for Reinforcement Learning
Paper • 2604.00698 • Published • 8
GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning
Paper • 2604.02721 • Published • 352
upvoted a paper 6 days ago