SWE-INTERACT: Reimagining SWE Benchmarks as User-Driven Long-Horizon Coding Sessions
Paper • 2606.30573 • Published • 5
Scale AI
company
Verified
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
SWE-INTERACT: Reimagining SWE Benchmarks as User-Driven Long-Horizon Coding Sessions
Not Every Rubric Teaches Equally: Policy-Aware Rubric Rewards for RLVR
anisha2102
submitted a
paper to Daily Papers 3 days ago
feyzaakyurek
published a
dataset 4 days ago
feyzaakyurek
published a
dataset 5 days ago
feyzaakyurek
updated 2
datasets 8 days ago
Update to revised rubrics (data_v2): 18,692 criteria
#2 opened 10 days ago
by 
feyzaakyurek
martin-pollack
updated a
dataset 17 days ago
martin-pollack
published a
dataset 18 days ago
utkarsh4430
submitted a
paper to Daily Papers about 1 month ago
yashmaurya-scale
updated a
dataset about 2 months ago
UdariMadhu
published a
dataset about 2 months ago
UdariMadhu
updated a
dataset about 2 months ago
yashmaurya-scale
published a
dataset about 2 months ago
tu-trinh-scale
authored 3
papers about 2 months ago
tu-trinh-scale
submitted a
paper to Daily Papers about 2 months ago
tu-trinh-scale
authored a
paper about 2 months ago
tu-trinh-scale
updated a
bucket 2 months ago
Judge prompt for ARS
2
#4 opened 3 months ago
by 
lematt1991