Zhengxi Lu

LZXzju's activity

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

upvoted a paper 1 day ago

Harness-S: Learning from Sibling Harnesses for Generalizable Agent Training

Paper • 2611.04277 • Published 5 days ago • 63

liked a dataset 4 days ago

vagrt/MemU-Bench-data

Viewer • Updated 9 days ago • 12.7k • 693 • 2

authored a paper 10 days ago

Work Agents: Systems, Capabilities, and Optimization

Paper • 2610.35845 • Published 13 days ago • 115

upvoted a paper 12 days ago

Work Agents: Systems, Capabilities, and Optimization

Paper • 2610.35845 • Published 13 days ago • 115

liked a dataset 13 days ago

077lukamagic/HybridCUA-8K

Updated about 1 month ago • 418 • 2

upvoted a collection 23 days ago

HybridCUA

Collection

Dataset & Model • 2 items • Updated Sep 29 • 2

upvoted a paper 29 days ago

ViSkill: Reinforcing VLM Agents with Evolving Visual-Native Skills

Paper • 2610.12403 • Published about 1 month ago • 13

authored a paper about 1 month ago

ComputerSD: Online Self-Distillation from Real-Time Feedback for Computer-Use Agents

Paper • 2609.40253 • Published Oct 1 • 8

upvoted 2 papers about 1 month ago

nanoMuse: An Open-Source Personal Agent for Every Device You Own

Paper • 2610.08699 • Published Oct 6 • 103

ComputerSD: Online Self-Distillation from Real-Time Feedback for Computer-Use Agents

Paper • 2609.40253 • Published Oct 1 • 8

authored a paper about 1 month ago

HybridCUA: Learning to Orchestrate GUI and CLI for Computer-Use Agents

Paper • 2609.38008 • Published Sep 29 • 25

upvoted a paper about 1 month ago

HybridCUA: Learning to Orchestrate GUI and CLI for Computer-Use Agents

Paper • 2609.38008 • Published Sep 29 • 25

submitted a paper to Daily Papers about 1 month ago

HybridCUA: Learning to Orchestrate GUI and CLI for Computer-Use Agents

Paper • 2609.38008 • Published Sep 29 • 25

authored a paper about 1 month ago

IterSynth: Rethinking Deep Search Agents via Role-Decoupled Iterative Synthesis

Paper • 2609.29444 • Published Sep 24 • 12

upvoted a paper about 1 month ago

IterSynth: Rethinking Deep Search Agents via Role-Decoupled Iterative Synthesis

Paper • 2609.29444 • Published Sep 24 • 12

authored 2 papers about 2 months ago

RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning

Paper • 2609.20784 • Published Sep 17 • 25

Reflect, Revise, Reuse: Training-Free Skill Evolution for GUI Agents

Paper • 2609.17653 • Published Sep 15 • 18

commented a paper about 2 months ago

RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning

Paper • 2609.20784 • Published Sep 17 • 25 •

3

upvoted a paper about 2 months ago

RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning

Paper • 2609.20784 • Published Sep 17 • 25

submitted a paper to Daily Papers about 2 months ago

RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning

Paper • 2609.20784 • Published Sep 17 • 25