arxiv:2505.20411
Andrei Andriushchenko
devkettle
ยท
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
5 days ago
Blockwise Advantage Estimation for Multi-Objective RL with Verifiable Rewards
authored
a paper
9 months ago
SWE-rebench: An Automated Pipeline for Task Collection and
Decontaminated Evaluation of Software Engineering Agents
Organizations
