LINKS

PROJECTS

SWE-rebench Leaderboard Live benchmark for coding agents on fresh real-world GitHub tasks, refreshed every month. Issue dates are tracked against model release dates, so possibly contaminated results are flagged. Reports resolved rate, pass@5, cost and tokens per problem. about · paper SWE-rebench 21,000+ executable SWE tasks from 3,400+ Python repositories, collected by a fully automated pipeline and validated by environment setup and test execution. Built for RL training and evaluation of code agents. dataset · paper · NeurIPS 2025 SWE-rebench V2 32,000+ executable SWE tasks in 20 programming languages from 3,600+ repositories, with pre-built images. An interactive setup agent installs each repository; an ensemble of LLM judges filters out unsound tasks. Plus 126,000+ additional tasks built from pull requests. dataset · PR tasks · code · paper · ICML 2026 ---

SELECTED PAPERS

SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents NeurIPS 2025 Datasets and Benchmarks · first author (145 citations) Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning arXiv 2025 (38 citations) SWE-rebench V2: Language-Agnostic SWE Task Collection at Scale ICML 2026 · first author (18 citations) Scaling Data Collection for Training Software Engineering Agents Nebius blog 2024 · first author (13 citations) Guided Search Strategies in Non-Serializable Environments with Applications to Software Engineering Agents ICML 2025 (12 citations) All papers → Google Scholar (citations as of Sep 2026) ---

TALKS & MEDIA

TALKS

SWE-rebench: Lessons from Evaluating Coding Agents on Real Software Engineering Tasks 2026-04 · AI Engineer Europe, London · video, 16 min Leveraging Training and Search for Better Software Engineering Agents 2024-12 · NeurIPS 2024, Vancouver · Nebius booth ---

PODCASTS & INTERVIEWS

From Dentistry to AI, Coding Agents, SWE-rebench 2026-03 · JetBrains Research Podcast · video ---

POSTERS

SWE-rebench V2: Language-Agnostic SWE Task Collection at Scale 2026-07 · ICML 2026, Seoul SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents 2025-12 · NeurIPS 2025, Datasets and Benchmarks Track ---

CONTACTS

GitHub github.com/ibragim-bad X x.com/ibragim_bad Telegram t.me/c0mmit Google Scholar scholar.google.com Email admin@ibragim.dev