机器人不再靠换大脑变强，而是让系统自己进化
我们一直以为让机器人更聪明，就是换一个更强的大模型当大脑。这篇论文反着来：大脑不变，让机器人周围的整套系统——记忆、技能库、决策流程——自己进化。它把每次执行任务的过程变成经验，自动诊断哪里不行，然后直接修改系统本身，而不是只改模型参数。结果很直接：同一个 GPT-5.5，套上这套进化机制后，在 EmbodiedBench 上成绩提升 27.8%;连开源模型 Qwen3.7-Plus 都被拉到和 GPT-5.5 几乎持平。更关键的是，这套进化出来的能力可以跨机器人迁移——在 A 机器人上学到的，直接用到 B 机器人上，不用重新训练。它不是你明天就能用的东西，但它指向一个方向：未来机器人不是靠换大脑变强，而是靠系统自己长本事。
📄 原文摘要(英文)
A foundation model should not act in isolation as an embodied agent. Yet, existing methods often optimize individual components of the agent stack, such as memory, context, skills, or action interfaces, rather than treating the supporting system itself as a unified policy. Moreover, interaction alone does not yield self-improvement unless execution experience is converted into persistent, validated system changes. We therefore propose RoboFoundry, the first embodied agentic framework that formulates this process as Self-Evolving System-as-Policy. RoboFoundry diagnoses capability gaps in decision-making and memory management, converts execution traces into validated task-specific system updates, and promotes recurring improvements to the general system. Evolution operates over two complementary surfaces: a context system that manages active internal context and persistent file-system memory, and a hierarchical skill system that organizes atomic skills, reusable compositions, and failure-conditioned recovery. A shared semantic interface separates embodiment-invariant decisions from embodiment-specific execution, allowing evolved system capabilities to transfer across heterogeneous robots. On EmbodiedBench, RoboFoundry achieves state-of-the-art performance, notably improving GPT-5.5 by 27.8%. It also brings Qwen3.7-Plus to near parity with GPT-5.5 (70.3% vs. 72.7%), showing consistent gains from system-as-policy evolution across foundation models. For long-horizon memory, RoboFoundry outperforms all baselines on RoboMemArena by at least 39.0%, even against methods assisted by external foundation models. On LIBERO-PRO, it further outperforms Cap-Agent0 by 243.8%-679.7% across all perturbation types. In real-world deployments, RoboFoundry demonstrates zero-shot transfer and online evolution across robots and tasks, highlighting its potential for fully autonomous embodied agents.