这篇论文讲的是怎么让AI智能体在更新技能或记忆时，不会把之前学好的东西忘了。它把更新和评估分开，效果比原来好10%以上，对做智能体的人很有用。
一篇关于持续学习的新论文提出了一种名为“受保护 harness 演化”的方法。该方法将 harness 组件的更新提议与实际提交分离开来。通过使用持续优化器和持续评估器，该方法在文本推理、多模态感知和开放世界交互等任务上实现了超过10%的相对增益。论文还定义并量化了“harness 级别遗忘”这一现象。
Banger paper on harness continual learning. (bookmark it) If you already are allowing your agents ...
Banger paper on harness continual learning. (bookmark it) If you already are allowing your agents to rewrite their own prompts, skills, or memory files, this one is worth your time. (bookmark it) Continual learning has always tracked what changes in the weights. Modern agents accumulate experience in the harness instead, across prompts, memories, tools, skills, and routing rules. What this means is that if you update any harness component, previously reliable behavior can break with the model completely untouched. The paper names that harness-level forgetting and provides a way to measure it. Guarded harness evolution separates proposing an update from committing it. A Continual Optimizer drafts a candidate harness from post-execution feedback, and a Continual Evaluator commits only after checking current improvement, historical retention, and validity. Relative gains exceed 10% across textual reasoning, multimodal perception, and open-world interaction. Paper: arxiv.org/abs/2608.19013 Track more trending AI papers in our academy: academy.dair.ai 💬 8 🔄 5 ❤️ 43 👀 3444 📊 23 ⚡