从模型扩展到系统扩展：扩展智能体AI中的“缰绳”
From Model Scaling to System Scaling: Scaling the Harness in Agentic AI
AI总结：
本文提出智能体AI的下一个瓶颈是系统扩展而非仅模型扩展，通过设计可审计、持久、模块化和可验证的架构（称为“缰绳”），并研究上下文治理、可信记忆和动态技能路由三大瓶颈，以推动智能体行为从模型能力向长期任务执行转化。
摘要：
本文研究智能体AI中下一个主要瓶颈是系统扩展，而不仅仅是模型扩展：围绕基础模型设计可审计、持久、模块化和可验证的架构。我们将这种转变称为扩展“缰绳”：将基础模型周围的结构化执行层视为设计、评估和优化的一等对象。尽管近期的大语言模型使智能体能够使用工具、检索信息、维护记忆并执行长期工作流，但评估仍以模型为中心，通常将智能体简化为最终任务成功，而将记忆、检索、工具使用、编排、验证和治理视为次要的实现细节。这种框架日益不足，因为智能体性能源于基础模型、记忆基质、上下文构建器、技能路由层、编排循环以及验证与治理层之间的交互。这些组件共同构成智能体缰绳，将模型能力转化为长期智能体行为。我们通过三个核心瓶颈研究扩展缰绳：上下文治理、可信记忆和动态技能路由，以及协调和约束它们的编排与治理机制。我们进一步概述了缰绳级基准的研究议程，超越一次性任务成功，测量轨迹质量、记忆卫生、上下文效率、通信保真度、验证成本和随时间的安全演化。为使讨论具体化，我们开发了CheetahClaws：https://github.com/SafeRL-Lab/cheetahclaws，一个Python原生参考缰绳，并将其与Claude Code和OpenClaw进行比较。我们的主要主张是，智能体AI的未来进展将同样依赖于系统设计和更强的模型。
英文摘要：
This paper studies the next major bottleneck in agentic AI as system scaling, not only model scaling: the design of auditable, persistent, modular, and verifiable architectures around foundation models. We refer to this shift as scaling the harness: treating the structured execution layer around a foundation model as a first-class object of design, evaluation, and optimization. Although recent large language models enable agents to use tools, retrieve information, maintain memory, and execute long-horizon workflows, evaluation remains largely model-centric, often reducing agents to final-task success while treating memory, retrieval, tool use, orchestration, verification, and governance as secondary implementation details. This framing is increasingly inadequate because agent performance emerges from the interaction among the foundation model, memory substrate, context constructor, skill-routing layer, orchestration loop, and verification-and-governance layer. Together, these components form the agent harness, which translates model capability into long-horizon agent behavior. We study scaling the harness through three core bottlenecks: context governance, trustworthy memory, and dynamic skill routing, together with the orchestration and governance mechanisms that coordinate and constrain them. We further outline a research agenda for harness-level benchmarks that go beyond one-shot task success to measure trajectory quality, memory hygiene, context efficiency, communication fidelity, verification cost, and safe evolution over time. To make the discussion concrete, we develop CheetahClaws: https://github.com/SafeRL-Lab/cheetahclaws, a Python-native reference harness, and compare it with Claude Code and OpenClaw. Our main claim is that future progress in agentic AI will depend as much on system design as on stronger foundation models.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
