Perry the Platypus PRO

AgPerry's activity

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

upvoted a paper 2 days ago

StopLoss: Teaching Agents to Predict Failure and Stop Early

Paper • 2610.25525 • Published 5 days ago • 12

upvoted a paper 13 days ago

MiniCorp: The Last Mile of the AI Agent Firm

Paper • 2610.05912 • Published 18 days ago • 39

upvoted a paper 16 days ago

World Editing: Intervening on Executable Worlds at Increasing Depth

Paper • 2610.02331 • Published 22 days ago • 31

upvoted 3 papers 21 days ago

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

Paper • 2609.36585 • Published 24 days ago • 42

Persona Dosing: Calibrated Activation Steering for Graded Trait Control

Paper • 2609.36388 • Published 25 days ago • 57

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

Paper • 2609.38597 • Published 24 days ago • 34

upvoted 5 papers about 1 month ago

ClawBench: Can AI Agents Complete Everyday Online Tasks?

Paper • 2604.08523 • Published Apr 9 • 369

Verifiable Social Reasoning for LLM Assistants

Paper • 2609.17496 • Published Sep 15 • 67

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

Paper • 2609.20519 • Published Sep 17 • 142

ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement

Paper • 2609.14857 • Published Sep 14 • 271

Dr. Claw: An AI Scientist Workspace for Vibe Research

Paper • 2609.00365 • Published Aug 31 • 409

upvoted 6 papers about 2 months ago

WebWorld: The Browser as a World Model for Self-Improving Web Code

Paper • 2608.30530 • Published Aug 31 • 10

S3Gym: Can LLMs Turn Self-Testing and Self-Judging into Self-Improvement?

Paper • 2608.31100 • Published Aug 31 • 149

HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?

Paper • 2609.01437 • Published Sep 1 • 521

Aspire: Can Models Self-Evolve from Vague Goals?

Paper • 2608.31111 • Published Aug 31 • 412

VGI-Bench: Probing Visual Intelligence in Video Generation Models

Paper • 2608.19583 • Published Aug 26 • 486

CyberFactory: Scaling Cyber Security Capabilities with Instances from the Wild

Paper • 2608.23181 • Published Aug 24 • 36

upvoted a collection 3 months ago

ClawBench & Agentic Web Benchmarks

Collection

ClawBench and related papers and open datasets for real-world web and computer-use agent evaluation. • 358 items • Updated 7 days ago • 2

upvoted 2 papers 3 months ago

Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models

Paper • 2607.12463 • Published Jul 14 • 305

Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation

Paper • 2607.05382 • Published Jul 9 • 83