LZX

zli12321's activity

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

New activity in deepseek-ai/DeepSeek-V4-Flash 3 days ago

Add LHTB eval result: 2/46 tasks solved (90-min budget, estimated)

#56 opened 3 days ago by

zli12321

updated a dataset 3 days ago

IntelligenceLab/LHTB-leaderboard

Viewer • Updated 3 days ago • 1.22k • 24.6k • 2

New activity in IntelligenceLab/LHTB-leaderboard 3 days ago

Upload folder using huggingface_hub

#7 opened 10 days ago by

zli12321

Upload folder using huggingface_hub

#8 opened 10 days ago by

zli12321

Upload folder using huggingface_hub

#9 opened 10 days ago by

zli12321

Upload submissions/long-horizon-terminal-bench/1.0/terminus-2__api_moonshot_kimi-k3/README.md with huggingface_hub

#4 opened 30 days ago by

zli12321

Upload submissions/long-horizon-terminal-bench/1.0-extended/README.md with huggingface_hub

#10 opened 10 days ago by

zli12321

New activity in MiniMaxAI/MiniMax-M3 3 days ago

Report LHTB as pass@0.95 (6.5) instead of mean reward

1

#27 opened 3 days ago by

zli12321

New activity in moonshotai/Kimi-K3 3 days ago

Add LHTB (Long-Horizon Terminal-Bench) eval result: 37.8

#174 opened 3 days ago by

zli12321

updated a dataset 3 days ago

IntelligenceLab/Long-Horizon-Terminal-Bench

Benchmark • Updated 3 days ago • 46 • 7.92k • 130

upvoted a paper 5 days ago

UI-Mate: Advancing Open-Weight Foundation GUI Agents with In-Context Demonstrations

Paper • 2608.15930 • Published 7 days ago • 46

New activity in IntelligenceLab/LHTB-leaderboard 12 days ago

Upload folder using huggingface_hub

#6 opened 17 days ago by

MrSusanovo

upvoted a paper 16 days ago

Recursive Synthesis for Long-Horizon Terminal Tasks

Paper • 2608.05466 • Published 16 days ago • 247

submitted a paper to Daily Papers 16 days ago

Recursive Synthesis for Long-Horizon Terminal Tasks

Paper • 2608.05466 • Published 16 days ago • 247

upvoted a collection 16 days ago

Recursive Synthesis for Long-Horizon Terminal Tasks

Collection

CC BY 4.0 datasets and SFT/RL checkpoints for recursive task synthesis; base-model and third-party terms still apply. • 6 items • Updated 12 days ago • 18

New activity in Zhongzhi1228/Recursive-Task-Synthesis 16 days ago

真是一千万以内最好的数据

#2 opened 16 days ago by

zli12321

liked a dataset 16 days ago

Zhongzhi1228/Recursive-Task-Synthesis

Viewer • Updated 16 days ago • 37.5k • 1.34k • 16

New activity in IntelligenceLab/LHTB-leaderboard 30 days ago

Upload folder using huggingface_hub

#3 opened 30 days ago by

zli12321

Add terminus-2 · gemini-3.6-flash (mean 0.390, solved 7/46)

#2 opened about 1 month ago by

ChengsongHuang

authored a paper about 1 month ago

Stale but Stable: Staleness-Adaptive Trust Regions for Stabilizing Asynchronous Reinforcement Learning

Paper • 2607.18722 • Published Jul 21 • 36