agentic-harness-engineering is queued for analysis. Crawling candidates and ranking them takes a few minutes. This page updates itself when the list exists — you can also come back later.
What is known so far comes from the other direction:
These projects were analysed and named agentic-harness-engineering among their alternatives. The relationship is not symmetric — how agentic-harness-engineering rates them is a separate judgement, made when agentic-harness-engineering is analysed in its own right.
calls agentic-harness-engineering “choose if you are targeting Terminal-Bench instead of SWE-bench with an evolved harness.”
SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]