PapersMulti-source76°

从模型缩放转向系统缩放:Agentic AI 的 Harness 设计

From Model Scaling to System Scaling: Scaling the Harness in Agentic AI

Why we picked it

做 Agent 系统架构的开发者会看到,当前只关注模型能力而忽视执行层设计的做法正在成为瓶颈——CheetahClaws 提供了一个可参考的系统级设计思路,值得研究。

本文提出 Agentic AI 的下一个瓶颈是系统缩放(system scaling),而非仅模型缩放。作者主张将基础模型周围的结构化执行层(即 harness)作为一等设计对象,包括记忆、检索、工具使用、编排、验证和治理等组件。

Body

研究识别出三大核心瓶颈:上下文治理、可信记忆和动态技能路由,并提出了超越单次任务成功率的基准测试框架。为验证观点,团队开发了 Python 原生参考实现 CheetahClaws,并与 Claude Code 和 OpenClaw 进行了对比。

核心结论是:未来 Agentic AI 的进步将同样依赖于系统设计,而不仅仅是更强的模型。

Original · arXiv cs.AI

From Model Scaling to System Scaling: Scaling the Harness in Agentic AI

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.

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Papers" desk. Key entities and technical topics under continuous tracking include agents.

Source attribution: curated from arXiv cs.AI (@Shangding Gu). Cross-source corroboration: 5 independent sources have covered this development (including IT之家, AI Will, Viking), confirming industry-wide signal strength.