Haoze Wu

WaitHZ's activity

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

authored a paper 3 days ago

The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution

Paper • 2510.25726 • Published 4 days ago • 41

upvoted a paper 4 days ago

The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution

Paper • 2510.25726 • Published 4 days ago • 41

liked a dataset 5 days ago

hkust-nlp/Toolathlon-Trajectories

Viewer • Updated 4 days ago • 5.82k • 274 • 8

upvoted a paper 12 days ago

LightMem: Lightweight and Efficient Memory-Augmented Generation

Paper • 2510.18866 • Published 12 days ago • 106

upvoted a collection about 1 month ago

DeepSeek-V3.2

Collection

2 items • Updated Sep 29 • 441

updated 2 collections about 2 months ago

MATH-Benchmark

Collection

5 items • Updated Sep 15

MATH-Training

Collection

2 items • Updated Sep 15

upvoted a paper about 2 months ago

WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents

Paper • 2509.06501 • Published Sep 8 • 78

authored 2 papers 2 months ago

ReCode: Updating Code API Knowledge with Reinforcement Learning

Paper • 2506.20495 • Published Jun 25 • 9

Model-Task Alignment Drives Distinct RL Outcomes

Paper • 2508.21188 • Published Aug 28 • 8

upvoted a paper 2 months ago

Model-Task Alignment Drives Distinct RL Outcomes

Paper • 2508.21188 • Published Aug 28 • 8

updated a collection 4 months ago

ReCode

Collection

2 items • Updated Jul 21

updated a dataset 4 months ago

zjunlp/ReCode-Train-Data

Viewer • Updated Jul 1 • 1.78k • 14 • 2

published a dataset 4 months ago

zjunlp/ReCode-Train-Data

Viewer • Updated Jul 1 • 1.78k • 14 • 2

updated a collection 4 months ago

ReCode

Collection

2 items • Updated Jul 21

liked a dataset 5 months ago

MiniMaxAI/SynLogic

Viewer • Updated Jul 2 • 49.3k • 351 • 93

commented a paper 8 months ago

HybridNorm: Towards Stable and Efficient Transformer Training via Hybrid Normalization

Paper • 2503.04598 • Published Mar 6 • 21 •

8