Bo Liu

Benjamin-eecs's activity

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

published an article 5 days ago

view article

Article

Your Inference Server is Secretly a Learner: Reef Infrastructure for Continual Self-Improving Agents

• 

quao627

•

5 days ago

• 15

upvoted an article 5 days ago

view article

Article

Your Inference Server is Secretly a Learner: Reef Infrastructure for Continual Self-Improving Agents

• 

quao627

•

5 days ago

• 15

updated 3 models 25 days ago

spade-rl/SPADE-Qwen3-4B-Games

Text Generation • 4B • Updated 25 days ago • 1.26k

spade-rl/SPADE-Qwen3-30B-A3B-Games

Text Generation • 31B • Updated 25 days ago • 1.15k

spade-rl/SPADE-Qwen3-8B-Games

Text Generation • 8B • Updated 25 days ago • 1.18k • 1

updated 6 datasets 25 days ago

spade-rl/SPADE-Grounding-Corpus-Games-15K

Viewer • Updated 25 days ago • 15k • 153

spade-rl/SPADE-Grounding-Corpus-ToolUse-15K

Viewer • Updated 25 days ago • 15.6k • 162 • 1

spade-rl/SPADE-Environment-Pool-GPT5.5-ToolUse

Viewer • Updated 25 days ago • 11k • 706 • 1

spade-rl/SPADE-Environment-Pool-GPT5.5-Games

Preview • Updated 25 days ago • 1.48k • 1

spade-rl/SPADE-Environments-ToolUse

Updated 25 days ago • 1.2k • 2

spade-rl/SPADE-Environments-Qwen3-30B-Games

Updated 25 days ago • 1.79k

updated a Space 29 days ago

Running

SPADE

♠

A model that writes and solves its own environments.

upvoted a paper about 1 month ago

EnvHarness: Awakening Static Worlds for Agent Learning

Paper • 2608.19880 • Published Aug 20 • 174

commented a paper about 1 month ago

SPADE: Self-Play in Adaptive Synthetic Executable Environments

Paper • 2608.19197 • Published Aug 19 • 54 •

2

authored a paper about 1 month ago

SPADE: Self-Play in Adaptive Synthetic Executable Environments

Paper • 2608.19197 • Published Aug 19 • 54

updated a collection about 1 month ago

SPADE

Collection

The full SPADE release: paper, model checkpoints, grounding corpora, and synthetic environments. • 4 items • Updated Aug 20 • 1

upvoted a paper about 1 month ago

SPADE: Self-Play in Adaptive Synthetic Executable Environments

Paper • 2608.19197 • Published Aug 19 • 54

upvoted a paper about 2 months ago

From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement

Paper • 2607.23802 • Published Jul 26 • 95

authored a paper about 2 months ago

From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement

Paper • 2607.23802 • Published Jul 26 • 95

liked a dataset 3 months ago

agents-last-exam/agents-last-exam

Viewer • Updated about 17 hours ago • 152 • 2k • 210