OSWorld2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks
Paper • 2606.29537 • Published • 22
AI & ML interests
computational linguistics, natural language processing
Recent Activity
View all activity
Papers
Forecasting Downstream Performance of LLMs With Proxy Metrics
Structured Distillation of Web Agent Capabilities Enables Generalization
xhluca
authored a
paper 6 days ago
virginiaceccatelli
updated a
dataset 8 days ago
Jinny1208
updated a
dataset 12 days ago
ilboglions
updated a
collection 15 days ago
ilboglions
published 2
datasets 15 days ago
ilboglions
published 2
models 15 days ago
ilboglions
updated 2
models 15 days ago
ilboglions
updated 2
datasets 15 days ago
JessicaOjo
updated a
Space 15 days ago
spandanagella
authored 4
papers 18 days ago
VectorGym: A Multitask Benchmark for SVG Code Generation, Sketching, and Editing
Paper • 2603.29852 • Published • 6
Mem-$π$: Adaptive Memory through Learning When and What to Generate
Paper • 2605.21463 • Published • 9
Toward Open Weight Models Without Risks: Separating Public and Private Capabilities in LLMs
Paper • 2606.21638 • Published • 8
PrivacyAlign: Contextual Privacy Alignment for LLM Agents
Paper • 2606.21710 • Published • 4