Perry the Platypus PRO

AgPerry's activity

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

New activity in TIGER-Lab/VideoScore2 2 days ago

Fix ZeroGPU-compatible PyTorch dependency versions

#2 opened 2 days ago by

AgPerry

upvoted 2 papers 7 days ago

ReGE: Stronger Agents through Experience Synthesis

Paper • 2610.33861 • Published 11 days ago • 14

Memory Tax: Dissecting the Net Value of Agent Memory

Paper • 2610.34073 • Published 10 days ago • 26

published an article 8 days ago

view article

Article

ClawBench Lite: inspect the task schema before running an agent

• 

AgPerry

•

8 days ago

upvoted a paper 14 days ago

StopLoss: Teaching Agents to Predict Failure and Stop Early

Paper • 2610.25525 • Published 17 days ago • 16

published an article 14 days ago

view article

Article

Inspecting generated video with VideoScore2: three questions to keep separate

• 

AgPerry

•

14 days ago

New activity in TIGER-Lab/WBArtifacts 18 days ago

Add selected WebsiteBench reference and agent website artifacts

#1 opened 18 days ago by

AgPerry

upvoted a paper 25 days ago

MiniCorp: The Last Mile of the AI Agent Firm

Paper • 2610.05912 • Published 30 days ago • 30

upvoted a paper 28 days ago

World Editing: Intervening on Executable Worlds at Increasing Depth

Paper • 2610.02331 • Published Oct 1 • 17

upvoted 6 papers about 1 month ago

Transformers Stop Thinking Too Early, and a Tiny LoRA Fixes It

Paper • 2609.36585 • Published Sep 29 • 27

Persona Dosing: Calibrated Activation Steering for Graded Trait Control

Paper • 2609.36388 • Published Sep 28 • 9

PixelUMM: Encoder-Free Unified Image and Video Understanding and Generation

Paper • 2609.38597 • Published Sep 29 • 31

ClawBench: Can AI Agents Complete Everyday Online Tasks?

Paper • 2604.08523 • Published Apr 9 • 118

Verifiable Social Reasoning for LLM Assistants

Paper • 2609.17496 • Published Sep 15 • 38

SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness

Paper • 2609.20519 • Published Sep 17 • 96

upvoted a paper about 2 months ago

ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement

Paper • 2609.14857 • Published Sep 14 • 59

published a dataset about 2 months ago

AgPerry/clone-garbage-collection

Updated Sep 11 • 64

upvoted a paper about 2 months ago

Dr. Claw: An AI Scientist Workspace for Vibe Research

Paper • 2609.00365 • Published Aug 31 • 38