All-Hands AI announced OpenHands 0.18, bringing architectural upgrades to its open-source software engineering agent. With a redesigned action planner, dynamic rollback search, and multi-agent code verification, OpenHands achieved a 53.4% solve rate on SWE-bench Verified, establishing a new SOTA among open-source agent frameworks.
Key Takeaways
- ✓Reaches a 53.4% solve rate on SWE-bench Verified, setting a record for open-source agents.
- ✓Integrates execution log introspection and rollback trees to avoid agent deadlock.
- ✓Supports Docker sandbox and cloud cluster deployment across Anthropic, OpenAI, and Ollama.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.