Coding-Agent Benchmarks Should Match Their Users' Task Flows Paper • 2610.09633 • Published 15 days ago • 14
Coding-Agent Benchmarks Should Match Their Users' Task Flows Paper • 2610.09633 • Published 15 days ago • 14
Coding-Agent Benchmarks Should Match Their Users' Task Flows Paper • 2610.09633 • Published 15 days ago • 14
JetBrains-Research/SWE-TaskFlow-SWE-Bench-Pro-Trajectories Viewer • Updated 10 days ago • 25.2k • 587 • 1
JetBrains-Research/SWE-TaskFlow-SWE-Bench-Pro-Trajectories Viewer • Updated 10 days ago • 25.2k • 587 • 1
SWE-TaskFlow Collection SWE-TaskFlow / SWE-Bench Pro hybrid scaffold datasets published under JetBrains-Research. • 0 items • Updated 19 days ago
JetBrains-Research/agent-trajectories-swe-bench-test-minus-verified Viewer • Updated Mar 29 • 1.79k • 229
JetBrains-Research/agent-trajectories-swe-bench-test-minus-verified Viewer • Updated Mar 29 • 1.79k • 229
LK Losses: Direct Acceptance Rate Optimization for Speculative Decoding Paper • 2602.23881 • Published Feb 27 • 18
Runtime error Agents SquircleCornersPrediction 📱 Detect and visualize squircle corners in iOS app icons
Runtime error Agents SquircleCornersPrediction 📱 Detect and visualize squircle corners in iOS app icons