Google 与 CMU 论文提出 Harmony Harness：多目标进化让自改进智能体更好保留安全收益

New Google and Carnegie Mellon paper finds self-improving agents hold on to security gains far better when security is evolved as a separate goal.

Agent harnesses, the prompts, tools and loops around a model, can now rewrite themselves from feedback. Most such systems chase a single score, like test pass rate, and the security gains they pick up mostly vanish on new tasks.

Harmony Harness evolves several harness versions, each pushed toward a different balance of passing tests and blocking exploits. It also keeps general fixes separate from benchmark-specific ones, and picks which pieces to use per task.

On unseen crash types in SecRepoBench, 66.7% of its fixes both worked and blocked the exploit, against 36.7% for the starting harness. It kept 55% of its security gain on those tasks, while the DGM baseline kept 0%.

When you let an agent improve itself, track security as its own score and check it on held-out tasks.