Ibragim's picture

9 6 4

Ibragim

ibragim-bad

·

AI & ML interests

Data for code agents

Recent Activity

updated a dataset 7 days ago

nebius/SWE-rebench-leaderboard

upvoted a paper 8 days ago

Blockwise Advantage Estimation for Multi-Objective RL with Verifiable Rewards

upvoted a paper 15 days ago

IMU-1: Sample-Efficient Pre-training of Small Language Models

View all activity

Organizations

authored a paper 7 months ago

Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning

Paper • 2508.03501 • Published Aug 5, 2025 • 59

authored a paper 9 months ago

SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents

Paper • 2505.20411 • Published May 26, 2025 • 93