Zhou Wenxuan

zwenxuan's activity

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

upvoted a paper 1 day ago

SkillHone: A Harness for Continual Agent Skill Evolution Through Persistent Decision History

Paper • 2606.08671 • Published 10 days ago • 24

liked a Space 3 days ago

Running on CPU Upgrade

647

ProtectBirds

🏃

647

Protect Birds

upvoted a paper 7 days ago

Escaping the Self-Confirmation Trap: An Execute-Distill-Verify Paradigm for Agentic Experience Learning

Paper • 2606.24428 • Published 10 days ago • 52

upvoted a paper 8 days ago

MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision

Paper • 2606.17162 • Published 18 days ago • 175

upvoted 2 papers 9 days ago

OpenRath: Session-Centered Runtime State for Agent Systems

Paper • 2606.19409 • Published 16 days ago • 77

DataClaw0: Agentic Tailoring Multimodal Data from Raw Streams

Paper • 2606.21337 • Published 14 days ago • 74

upvoted a paper 10 days ago

Skill-MAS: Evolving Meta-Skill for Automatic Multi-Agent Systems

Paper • 2606.18837 • Published 16 days ago • 57

upvoted 3 papers 12 days ago

Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs

Paper • 2605.30611 • Published May 28 • 250

Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts

Paper • 2606.05922 • Published 28 days ago • 69

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

Paper • 2606.18023 • Published 17 days ago • 209

liked a model 12 days ago

ISdept/Wilro-ed-117k-l16

0.8B • Updated 12 days ago • 23 • 1

upvoted 3 papers 13 days ago

Looped World Models

Paper • 2606.18208 • Published 17 days ago • 475

Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance

Paper • 2606.19195 • Published 16 days ago • 139

DragMesh-2: Physically Plausible Dexterous Hand-Object Interaction with Articulated Objects

Paper • 2606.15133 • Published 20 days ago • 74

upvoted a paper 15 days ago

Learning from the Self-future: On-policy Self-distillation for dLLMs

Paper • 2606.18195 • Published 17 days ago • 76

upvoted a paper 18 days ago

OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data

Paper • 2606.13432 • Published 22 days ago • 113

upvoted 2 papers 20 days ago

ABot-Earth 0.5: Generative 3D Earth Model

Paper • 2606.09967 • Published 25 days ago • 486

From Correctness to Utility: Gain-Based Prefix Evaluation for LLM Reasoning

Paper • 2606.07190 • Published 28 days ago • 35

upvoted 2 papers 21 days ago

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

Paper • 2606.12087 • Published 23 days ago • 77

Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks

Paper • 2606.12344 • Published 23 days ago • 70