Google open-sources Harness², GLM-5 score improves by 11.5 points

Google Research's open-source AI toolchain self-improvement framework Harness² allows AI Agents to automatically modify system prompts, memories, skills, tool rules, scripts, and plugins without retraining the model. The project is licensed under the Apache 2.0 license and supports OpenCode and Codex. Its core mechanism enables the Agent to learn through trial and error, proposing several improvement plans when encountering new tasks, which are then executed and compared by different versions of the Agent, ultimately combining to form a more suitable solution.

Even without a standard answer, the system can seek improvement directions based on the actual execution process. After the task is completed, the system remembers which modifications were effective and the reasons, for reference in similar future problems. Google tested using GLM-5 and Gemini 3.5 Flash. On WorkBuddy-Bench, GLM-5 paired with OpenCode improved its average score from 64.2 to 75.7 after just one round of optimization, surpassing the unoptimized Gemini 3.5 Flash's score of 72.4.

In legal task testing, the pass rate for GLM-5's partial scoring criteria increased from 59.6% to 71.4%. In the experiment, Claude Opus 4.8 was defaulted to propose and implement improvements, while GLM-5 and Gemini were primarily responsible for executing tasks, not entirely relying on themselves for evolution. Domestic developer Joseph Zhou demonstrated an experiment where Harness² was integrated with Jev 1.14, claiming that the performance on visual tasks continuously improved.