Tianyu PRO

iLOVE2D

·

AI & ML interests

None yet

Recent Activity

new activity about 18 hours ago

SciAILab/OSWorld-Science-data:chem struct_03/struct_07: references that cannot exist in 3D

new activity 1 day ago

SciAILab/OSWorld-Science-data:chem retro: molecular-weight tolerance 0.05 -> 1.0 g/mol

new activity 8 days ago

SciAILab/OSWorld-Science-data:Unified Linux VM image (vm/ubuntu_unified.qcow2) and grading revision

View all activity

Organizations

upvoted a paper 9 days ago

CompoWorld: Compositional Environment Scaling for General Agents

Paper • 2609.33665 • Published 14 days ago • 41

upvoted 2 papers 10 days ago

AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks

Paper • 2609.38288 • Published 12 days ago • 137

OSWorld-Science: A Benchmark of Computer Use Agents for Learning and Using Scientific Software

Paper • 2609.39903 • Published 11 days ago • 64

upvoted a paper 27 days ago

Occamy-1.0: Open Pareto-frontier 35B Intelligence for Co-work

Paper • 2609.11977 • Published Sep 4 • 119

upvoted a paper about 1 month ago

CUADebug: Diagnosing and Repairing Computer-Use Agent Failures

Paper • 2608.02643 • Published Sep 6 • 3

upvoted 2 papers 2 months ago

Business Arena: Benchmarking LLM Agents in a Realistic Marketplace

Paper • 2608.08621 • Published Aug 9 • 22

OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models

Paper • 2607.28609 • Published Jul 30 • 75

upvoted a paper 4 months ago

Benchmarking AI Agents for Addressing Scientific Challenges Across Scales

Paper • 2606.12736 • Published Jun 10 • 6

upvoted a paper about 1 year ago

DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search

Paper • 2509.25454 • Published Sep 29, 2025 • 148