Perry the Platypus PRO

AgPerry

·

AI & ML interests

None yet

Recent Activity

upvoted a paper about 11 hours ago

ReGE: Stronger Agents through Experience Synthesis

upvoted a paper about 15 hours ago

Memory Tax: Dissecting the Net Value of Agent Memory

published an article 2 days ago

ClawBench Lite: inspect the task schema before running an agent

View all activity

Organizations

New activity in TIGER-Lab/WBArtifacts 12 days ago

Add selected WebsiteBench reference and agent website artifacts

#1 opened 12 days ago by

New activity in TIGER-Lab/ClawBench 3 months ago

ClawBench V2: reproducible real-world web-agent evaluation

#2 opened 3 months ago by

New activity in huggingface/HuggingDiscussions 3 months ago

[FEEDBACK] Daily Papers

#32 opened over 2 years ago by

commented a paper 3 months ago

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

Paper • 2607.12463 • Published Jul 14 • 305 •

commented a paper 6 months ago

RewardHarness: Self-Evolving Agentic Post-Training

Paper • 2605.08703 • Published May 9 • 240 •

New activity in TIGER-Lab/MMLU-Pro 7 months ago

how to download responses of specific models

#45 opened 8 months ago by