Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning
Paper
•
2508.03501
•
Published
•
59
Mariia Trofimova
vim-ary
AI & ML interests
NLP
Recent Activity
liked
a dataset
2 days ago
nebius/SWE-rebench-openhands-trajectories
updated
a dataset
4 days ago
nebius/SWE-rebench-openhands-trajectories
new activity
6 days ago
nebius/SWE-rebench-openhands-Qwen3-30B-A3B:Exactly what I have been looking for.
Organizations
upvoted
a
paper
5 months ago