这篇论文提出了LOGOS，一个让AI团队自我进化同时受人类控制的框架。它不替换现有系统，而是增加了治理层，确保问责。
LOGOS是一个可插拔层，用于强化现有多智能体框架，而不是替换它们。它编译异构多模态输入（文档、图像、音频、表格、数据库、API、人类指令）为版本化的agent packs，包含智能体、工具、知识、测试、权限和策略。操作中，LOGOS将智能体活动转化为可审计的事件轨迹，并在框架和后端之间应用失败关闭验证。每个学习到的提示、记忆、技能、工具、角色或工作流被视为未信任发布候选，直到通过保留执行证据、人类控制的策略和明确授权才允许升级。该架构实现了可验证的人-智能体循环工程，支持智能体提议改进而人类控制目标、权限和不可逆操作。
LOGOS: A Living Logic for AI Agent Teams That Evolve With Humans
AI agents are evolving from answer engines into persistent teams that use tools, delegate work, learn from experience, and modify the artifacts that shape their future behavior. The defining question for deployment is no longer merely what agents can do, but who controls what they are allowed to become. We introduce logos, a pluggable layer for self-evolution and governance that strengthens existing multiagent frameworks rather than replacing them. logos compiles heterogeneous multimodal inputs, including documents, images, audio, tables, databases, APIs, and human instructions into versioned agent packs containing agents, tools, knowledge, tests, permissions, and policies. During operation, it transforms agent activity into portable, auditable event traces and applies fail-closed verification across frameworks and backends. Every learned prompt, memory, skill, tool, role, or workflow remains an untrusted release candidate until held-out execution evidence, human-controlled policy, and explicit authorization permit its promotion. This architecture enables "verifiable human-agent loop engineering": agents can act, ask, learn, and propose improvements, while humans can steer objectives, permissions, approvals, and irreversible actions without interrupting continuous operation. logos provides a living logic for accountable automation. Agents may evolve at machine speed, but only evidence and human authority can close the loop.