pangpangxuan

pangxuan's activity

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

upvoted a paper 1 day ago

1% of Tokens Can Be Enough: On Gradient Estimation in On-Policy Distillation

Paper • 2609.24432 • Published 4 days ago • 16

upvoted 3 papers 3 days ago

GameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay

Paper • 2609.25001 • Published 4 days ago • 130

RRSI: Regularized Recursive Self-Improvement of Agent Harnesses

Paper • 2609.24972 • Published 4 days ago • 201

Grounded Skill Synthesis from Code at Scale for Agentic Intelligence

Paper • 2609.05571 • Published 21 days ago • 114

upvoted 5 papers 4 days ago

Scaling Automatic Research Agents via World Models

Paper • 2608.12564 • Published 27 days ago • 478

On-Policy Self-Distillation without Any Supervision

Paper • 2608.06296 • Published Aug 9 • 180

CodeMidas: Scaling Agentic Coding RL Environments from Code Itself

Paper • 2609.22068 • Published 7 days ago • 131

RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents

Paper • 2609.22000 • Published 7 days ago • 78

EvoOntology: A Self-Evolving Ontology Layer for Data Agents

Paper • 2609.15779 • Published 11 days ago • 151

upvoted 2 papers 6 days ago

Can MiniMax-H3 Reason About the Physical World? An Evaluation of Omni-Modal Generative Model

Paper • 2609.18323 • Published 9 days ago • 130

DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression

Paper • 2609.19969 • Published 8 days ago • 178

upvoted a paper 9 days ago

Continual Learning Mechanisms Compose for Long-Horizon Memorization

Paper • 2609.06986 • Published 18 days ago • 373

upvoted 3 papers 10 days ago

T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks

Paper • 2609.11042 • Published 15 days ago • 63

NCP-ArchPreview Technical Report: Moving towards Latent Space Language Models through Next Concept Prediction

Paper • 2609.10715 • Published 16 days ago • 329

Dream-RSI: Recursive Self-Improvement through Evolving Worlds

Paper • 2609.14858 • Published 11 days ago • 246

upvoted a paper 15 days ago

NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness

Paper • 2609.08183 • Published 17 days ago • 174

upvoted 3 papers 17 days ago

Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills

Paper • 2609.02749 • Published 23 days ago • 402

Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnesses

Paper • 2608.24876 • Published about 1 month ago • 30

Aspire: Can Models Self-Evolve from Vague Goals?

Paper • 2608.31111 • Published 25 days ago • 169

upvoted a paper 18 days ago

Rethinking On-Policy Distillation of Large Language Models II: One Training Example

Paper • 2609.04172 • Published 22 days ago • 101