When "Correct" Is Not Safe: Can We Trust Functionally Correct Patches Generated by Code Agents?
Paper
•
2510.17862
•
Published
•
6
James Song
shxjames
·
AI & ML interests
Transformers, NLP, ML
Recent Activity
authored
a paper
2 months ago
When "Correct" Is Not Safe: Can We Trust Functionally Correct Patches
Generated by Code Agents?
upvoted
a
paper
3 months ago
Prosperity before Collapse: How Far Can Off-Policy RL Reach with Stale
Data on LLMs?
Organizations
