Miraclys

Miraclys's activity

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

upvoted a paper 6 days ago

Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent

Paper • 2606.30616 • Published 8 days ago • 90

upvoted a paper 7 days ago

LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing

Paper • 2606.26740 • Published 12 days ago • 82

upvoted a paper 19 days ago

LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling

Paper • 2606.18023 • Published 21 days ago • 209

upvoted a paper 25 days ago

FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents

Paper • 2606.12087 • Published 27 days ago • 77

upvoted a paper about 2 months ago

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

Paper • 2605.10344 • Published May 11 • 51

upvoted a paper 2 months ago

ClawGym: A Scalable Framework for Building Effective Claw Agents

Paper • 2604.26904 • Published Apr 29 • 54

upvoted 2 papers 5 months ago

SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training

Paper • 2602.03411 • Published Feb 3 • 39

SWE-World: Building Software Engineering Agents in Docker-Free Environments

Paper • 2602.03419 • Published Feb 3 • 41