Song Huatong

XXsongLALA's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper about 6 hours ago

TMAS: Scaling Test-Time Compute via Multi-Agent Synergy

Paper • 2605.10344 • Published 1 day ago • 42

upvoted a paper 12 days ago

ClawGym: A Scalable Framework for Building Effective Claw Agents

Paper • 2604.26904 • Published 14 days ago • 50

upvoted a paper 27 days ago

Toward Autonomous Long-Horizon Engineering for ML Research

Paper • 2604.13018 • Published 29 days ago • 34

updated a collection about 2 months ago

SWE Agent Series

Collection

Models trained by SWE-Master and SWE-World, including both policy models and verifiers. • 13 items • Updated Mar 23 • 3

upvoted a collection about 2 months ago

SWE Agent Series

Collection

Models trained by SWE-Master and SWE-World, including both policy models and verifiers. • 13 items • Updated Mar 23 • 3

updated a model about 2 months ago

RUC-AIBOX/SWE-World-SWR-72B-w-cot

73B • Updated Mar 23 • 1

published a model about 2 months ago

RUC-AIBOX/SWE-World-SWR-72B-w-cot

73B • Updated Mar 23 • 1

updated a model about 2 months ago

RUC-AIBOX/SWE-World-SWT-72B-w-cot

73B • Updated Mar 23 • 8

published a model about 2 months ago

XXsongLALA/SWE-World-SWR-72B-wo-cot

Updated Mar 23

upvoted a paper 2 months ago

BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?

Paper • 2603.03194 • Published Mar 3 • 57

updated a collection 3 months ago

SWE Agent Series

Collection

Models trained by SWE-Master and SWE-World, including both policy models and verifiers. • 13 items • Updated Mar 23 • 3