Agents
self-harness: harnesses that improve themselves spoiler alert, it's all loop engineering! 1. weakness mining - run agent and observe failure…
self-harness: harnesses that improve themselves spoiler alert, it's all loop engineering! 1. weakness mining - run agent and observe failures 2. propose improvements to the harness 3. confirm improvem
self-harness: harnesses that improve themselves spoiler alert, it's all loop engineering! 1. weakness mining - run agent and observe failures 2. propose improvements to the harness 3. confirm improvements are beneficial and don't cause other regressions and then you loop! the paper: https://arxiv.org/pdf/2606.09498 powered by deepagents: https://github.com/langchain-ai/deepagents
Source: Harrison Chase (X) | 2026-06-23