Kangheng Liu

kanghengliu's activity

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

updated a collection about 2 months ago

CORE-bench v1.1

Collection

Benchmark for AI agents on scientific reproducibility — mainline (39) and OOD (19) splits derived from Code Ocean capsules. • 2 items • Updated May 5

updated 2 datasets about 2 months ago

agent-evals/core-bench-v1.1-ood

Viewer • Updated May 5 • 19 • 18

agent-evals/core-bench-v1.1-mainline

Viewer • Updated May 5 • 39 • 42

published 2 datasets about 2 months ago

agent-evals/core-bench-v1.1-ood

Viewer • Updated May 5 • 19 • 18

agent-evals/core-bench-v1.1-mainline

Viewer • Updated May 5 • 39 • 42

upvoted a paper 4 months ago

Towards a Science of AI Agent Reliability

Paper • 2602.16666 • Published Feb 18 • 16

updated a dataset 5 months ago

agent-evals/hal_traces

Updated Feb 1 • 2.54k • 6

updated 2 datasets 7 months ago

agent-evals/hal_traces

Updated Feb 1 • 2.54k • 6

agent-evals/hal_traces

Updated Feb 1 • 2.54k • 6