When "Correct" Is Not Safe: Can We Trust Functionally Correct Patches Generated by Code Agents?
Paper
•
2510.17862
•
Published
•
6
•
2
Haizhong
haizhongzheng
AI & ML interests
Efficient machine learning
Recent Activity
commented on
a paper
23 days ago
When "Correct" Is Not Safe: Can We Trust Functionally Correct Patches
Generated by Code Agents?
upvoted
a
paper
about 1 month ago
Prosperity before Collapse: How Far Can Off-Policy RL Reach with Stale
Data on LLMs?
Organizations
commented
a
paper
23 days ago
commented
a
paper
about 1 month ago