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

Documenti analoghi

• SWE-rebench V2: Language-Agnostic SWE Task Collection at Scale
  di: Badertdinov, Ibragim, et al.
  Pubblicazione: (2026)
• Guided Search Strategies in Non-Serializable Environments with Applications to Software Engineering Agents
  di: Zainullina, Karina, et al.
  Pubblicazione: (2025)
• Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning
  di: Golubev, Alexander, et al.
  Pubblicazione: (2025)
• Blockwise Advantage Estimation for Multi-Objective RL with Verifiable Rewards
  di: Pavlenko, Kirill, et al.
  Pubblicazione: (2026)
• From SWE-ZERO to SWE-HERO: Execution-free to Execution-based Fine-tuning for Software Engineering Agents
  di: Ludwig, Nikolai, et al.
  Pubblicazione: (2026)