pangpangxuan

pangxuan's activity

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

upvoted a paper about 2 hours ago

Recursive Game Creator: An Agentic Product-Level Experience-Oriented Game Harness

Paper • 2610.08621 • Published 8 days ago • 94

upvoted a paper about 22 hours ago

LexReward: A Taxonomy-Driven Reward Framework for Legal Language Models

Paper • 2609.39071 • Published 14 days ago • 67

upvoted a paper 1 day ago

MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement

Paper • 2610.11959 • Published 6 days ago • 82

upvoted a paper 6 days ago

False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents

Paper • 2609.39102 • Published 14 days ago • 654

upvoted 3 papers 7 days ago

LoopVL: Recurrent Visual Intelligence

Paper • 2609.38426 • Published 15 days ago • 478

On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics

Paper • 2609.35259 • Published 16 days ago • 203

Scaling Trajectories for Complex Tasks through Recursive Self-Rewrite

Paper • 2610.02826 • Published 12 days ago • 103

upvoted 3 papers 13 days ago

Groupwise Agentic Grading and Advantage Redistribution for Code Agent RL

Paper • 2609.32577 • Published 18 days ago • 106

LongCat-DeepResearch Technical Report

Paper • 2609.36071 • Published 16 days ago • 74

Raven: The Harness of Harnesses for Composable Agentic Intelligence

Paper • 2609.33439 • Published 17 days ago • 675

upvoted a paper 14 days ago

Diffusion Reward Models

Paper • 2609.33803 • Published 17 days ago • 35

upvoted a paper 15 days ago

Training Object Permanence in World Models

Paper • 2609.28654 • Published 21 days ago • 181

upvoted a collection 15 days ago

MiMo-V2.6

Collection

5 items • Updated 16 days ago • 131

upvoted 2 papers 16 days ago

SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue

Paper • 2609.26780 • Published 22 days ago • 103

HappyWorld-Bench

Paper • 2609.24308 • Published 23 days ago • 59

upvoted a paper 20 days ago

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

Paper • 2609.24432 • Published 23 days ago • 16

upvoted 3 papers 21 days ago

GameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay

Paper • 2609.25001 • Published 23 days ago • 132

RRSI: Regularized Recursive Self-Improvement of Agent Harnesses

Paper • 2609.24972 • Published 23 days ago • 229

Grounded Skill Synthesis from Code at Scale for Agentic Intelligence

Paper • 2609.05571 • Published Sep 4 • 119

upvoted a paper 22 days ago

Scaling Automatic Research Agents via World Models

Paper • 2608.12564 • Published Aug 29 • 489