自主代理系统在部署后基本上是静态的:，它们不会从用户交互中学习,，并且反复出现的故障会持续存在，直到下一个人工驱动的更新发布修复为止。自我进化代理已经在响应,中出现，但都将进化限制在文本可变工件——技能文件,提示配置,内存模式,工作流程图——并且使代理工具保持不变。由于路由, 钩子排序, 状态不变量, 和调度存在于代码中而不是任何文本工件, 中，因此从文本层物理上无法访问整个结构故障类。我们认为，源级适应从根本上来说是一种更通用的媒介:，它是图灵完备的,，是每个文本可变范围的严格超集, 确定性地生效，而不是通过基本模型合规性,，并且在长上下文漂移下不会受到侵蚀。我们提出了 MOSS, 一个系统，可以在生产代理基板上在源代码级别执行自重写。每次演变都锚定在一批自动策划的生产故障证据上，并通过确定性多阶段管道进行; 代码修改被委托给可插入的外部编码代理 CLI，而 MOSS 保留阶段排序和判决。通过在临时试验工作人员, 中根据候选图像重放批次来验证候选者，然后通过用户同意门控, 就地容器交换和运行状况探测门控回滚来升级。在 OpenClaw, 上，MOSS 在一个周期内将四任务平均评分从 0.25 提高到 0.61，无需人工干预。
Autonomous agentic systems are largely static after deployment: they do not learn from user interactions, and recurring failures persist until the next human-driven update ships a fix. Self-evolving agents have emerged in response, but all confine evolution to text-mutable artifacts -- skill files, prompt configurations, memory schemas, workflow graphs -- and leave the agent harness untouched. Since routing, hook ordering, state invariants, and dispatch live in code rather than in any text artifact, an entire class of structural failure is physically unreachable from the text layer. We argue that source-level adaptation is a fundamentally more general medium: it is Turing-complete, a strict superset of every text-mutable scope, takes effect deterministically rather than through base-model compliance, and does not erode under long-context drift. We present MOSS, a system that performs self-rewriting at the source level on production agentic substrates. Each evolution is anchored to an automatically curated batch of production-failure evidence and proceeds through a deterministic multi-stage pipeline; code modification is delegated to a pluggable external coding-agent CLI while MOSS retains stage ordering and verdicts. Candidates are verified by replaying the batch against the candidate image in ephemeral trial workers, then promoted via user-consent-gated, in-place container swap with health-probe-gated rollback. On OpenClaw, MOSS lifts a four-task mean grader score from 0.25 to 0.61 in a single cycle without human intervention.
科目: 人工智能 (cs.AI); 机器学习 (cs.LG)
Subjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)