本文研究了代理人工智能的下一个主要瓶颈，即系统扩展,，不仅是模型扩展:，还有可审计,、持久,、模块化, 的设计以及围绕基础模型的可验证架构。我们将这种转变称为扩展工具:，将基础模型周围的结构化执行层视为设计, 评估, 和优化的一流对象。尽管最近的大型语言模型使代理能够使用工具,检索信息,维护内存,并执行长期工作流程,评估仍然主要以模型为中心,通常会降低代理的最终任务成功率，同时将内存,检索,工具使用,编排,验证,和治理视为次要实现细节。这种框架越来越不够充分，因为代理性能来自于基础模型,内存基底,上下文构造器,技能路由层,编排循环,和验证与治理层之间的交互。 , 这些组件共同构成了代理工具,，它将模型能力转化为长期代理行为。我们研究通过三个核心瓶颈:上下文治理,可信内存,和动态技能路由,以及协调和约束它们的编排和治理机制来扩展该工具。我们进一步概述了线束级基准测试的研究议程，该议程超越了一次性任务成功的范围，以衡量轨迹质量,内存卫生,上下文效率,通信保真度,验证成本,和随着时间的推移安全演变。为了使讨论具体,，我们开发了 CheetahClaws:，此 https URL, 是一个 Python 原生参考工具,，并将其与 Claude Code 和 OpenClaw 进行比较。我们的主要主张是，代理人工智能的未来进展将不仅取决于更强大的基础模型，还取决于系统设计。

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: this https URL, 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.

科目: 人工智能 (cs.AI); 机器学习 (cs.LG)

Subjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)