GTAlign

GTAlign's activity

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

zsqzz 

authored a paper about 1 month ago

Agents' Last Exam

Paper • 2606.05405 • Published Jun 3 • 378

zsqzz 

authored 2 papers 2 months ago

Who Prices Cognitive Labor in the Age of Agents? Compute-Anchored Wages

Paper • 2605.05558 • Published May 8 • 3

The Many Faces of On-Policy Distillation: Pitfalls, Mechanisms, and Fixes

Paper • 2605.11182 • Published May 11 • 5

zsqzz 

submitted 2 papers to Daily Papers 2 months ago

The Many Faces of On-Policy Distillation: Pitfalls, Mechanisms, and Fixes

Paper • 2605.11182 • Published May 11 • 5

Who Prices Cognitive Labor in the Age of Agents? Compute-Anchored Wages

Paper • 2605.05558 • Published May 8 • 3

zsqzz 

authored 3 papers 2 months ago

Rethinking Memory Mechanisms of Foundation Agents in the Second Half: A Survey

Paper • 2602.06052 • Published Jan 14 • 7

Probing the Knowledge Boundary: An Interactive Agentic Framework for Deep Knowledge Extraction

Paper • 2602.00959 • Published Feb 1

Agentic AI Systems Should Be Designed as Marginal Token Allocators

Paper • 2605.01214 • Published May 2 • 4

zsqzz 

submitted a paper to Daily Papers 2 months ago

Agentic AI Systems Should Be Designed as Marginal Token Allocators

Paper • 2605.01214 • Published May 2 • 4

zsqzz 

authored a paper 6 months ago

OpenTinker: Separating Concerns in Agentic Reinforcement Learning

Paper • 2601.07376 • Published Jan 12 • 7

zsqzz 

submitted a paper to Daily Papers 6 months ago

OpenTinker: Separating Concerns in Agentic Reinforcement Learning

Paper • 2601.07376 • Published Jan 12 • 7

zsqzz 

updated 5 models 8 months ago

GTAlign/Qwen2.5-3B-Medium-110step

Text Generation • 3B • Updated Nov 3, 2025 • 4

GTAlign/Qwen2.5-3B-Full-160step

Text Generation • 3B • Updated Nov 3, 2025 • 2

GTAlign/Qwen2.5-3B-Math-140step

Text Generation • 3B • Updated Nov 3, 2025 • 2

GTAlign/Qwen2.5-3B-AbgQA-140step

Text Generation • 3B • Updated Nov 3, 2025 • 2

GTAlign/Qwen2.5-3B-WildGuard-140step

Text Generation • 3B • Updated Nov 3, 2025 • 3

zsqzz 

authored 2 papers 9 months ago

Multi-Agent Evolve: LLM Self-Improve through Co-evolution

Paper • 2510.23595 • Published Oct 27, 2025 • 14

GTAlign: Game-Theoretic Alignment of LLM Assistants for Mutual Welfare

Paper • 2510.08872 • Published Oct 10, 2025 • 4

zsqzz 

updated a Space 9 months ago

No application file

Agents

README

🐠

zsqzz 

published a model 9 months ago

GTAlign/Qwen2.5-3B-Full-160step

Text Generation • 3B • Updated Nov 3, 2025 • 2