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

• URL: http://arxiv.org/abs/2605.26112v1
• Date: Mon, 25 May 2026 17:59:36 GMT
• Title: From Model Scaling to System Scaling: Scaling the Harness in Agentic AI
• Abstract summary: This paper studies the next major bottleneck in agentic AI as system scaling.<n>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.<n>Our main claim is that future progress in agentic AI will depend as much on system design as on stronger foundation models.
• Score: 4.802305157491253
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• From Question Answering to Task Completion: A Survey on Agent System and Harness Design [67.8241530947325]
  This survey examines LLM-based agents through a model-harness lens.<n>We first clarify the functional definition of agents and the implementation view of an LLM-based agent as a foundation model and an execution harness.<n>We then analyze the limits of model-centric scaling, trace four paradigms of agent engineering, and decompose the execution harness into six coupled runtime responsibilities.
  arXiv  Detail & Related papers  (2026-06-14T05:40:16Z)
• CogScale: Scalable Benchmark for Sequence Processing [1.8853398065417313]
  Testing a new architecture often requires scaling up to massive datasets and models, leading to vast computational costs and slow iteration cycles.<n>We propose CogScale, a benchmark of 14 scalable synthetic tasks designed to isolate and evaluate specific cognitive and memory abilities.<n>Our results show that while classical RNNs and Echo State Networks excel at basic retention within strict parameter budgets, only attention mechanisms and modern state-space models consistently maintain high performance.
  arXiv  Detail & Related papers  (2026-05-19T12:32:52Z)
• Code as Agent Harness [107.31925305395957]
  In emerging agentic systems, code is no longer only a target output.<n>Code increasingly serves as an operational substrate for agent reasoning, acting, environment modeling, and execution-based verification.<n>This survey provides a unified roadmap toward executable, verifiable, and stateful AI agent systems.
  arXiv  Detail & Related papers  (2026-05-18T17:59:03Z)
• Understanding by Reconstruction: Reversing the Software Development Process for LLM Pretraining [66.89012795621349]
  Large Language Models (LLMs) often struggle with the deep, long-horizon reasoning required for complex software engineering.<n>We propose a novel paradigm: understanding via reconstruction.<n>We introduce a framework that synthesizes latent agentic trajectories using a multi-agent simulation.
  arXiv  Detail & Related papers  (2026-03-11T09:23:20Z)
• El Agente Gráfico: Structured Execution Graphs for Scientific Agents [7.47895130442454]
  We present El Agente Grfico, a single-agent framework that embeds large language models (LLMs)-driven decision-making within a type-safe execution environment.<n>Central to our approach is a structured abstraction of scientific concepts and an object-graph mapper that represents computational state as typed Python objects.<n>We evaluate the system by developing an automated benchmarking framework across a suite of university-level quantum chemistry tasks.
  arXiv  Detail & Related papers  (2026-02-19T23:47:05Z)
• Beyond Quantity: Trajectory Diversity Scaling for Code Agents [51.71414642763219]
  Trajectory Diversity Scaling is a data synthesis framework for code agents that scales performance through diversity rather than raw volume.<n> TDScaling integrates four innovations: (1) a Business Cluster mechanism that captures real-service logical dependencies; (2) a blueprint-driven multi-agent paradigm that enforces trajectory coherence; and (3) an adaptive evolution mechanism that steers toward long-tail scenarios.
  arXiv  Detail & Related papers  (2026-02-03T07:43:03Z)
• Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models [78.73992315826035]
  We introduce Youtu-LLM, a lightweight language model that harmonizes high computational efficiency with native agentic intelligence.<n>Youtu-LLM is pre-trained from scratch to systematically cultivate reasoning and planning capabilities.
  arXiv  Detail & Related papers  (2025-12-31T04:25:11Z)
• Every Step Counts: Decoding Trajectories as Authorship Fingerprints of dLLMs [63.82840470917859]
  We show that the decoding mechanism of dLLMs can be used as a powerful tool for model attribution.<n>We propose a novel information extraction scheme called the Directed Decoding Map (DDM), which captures structural relationships between decoding steps and better reveals model-specific behaviors.
  arXiv  Detail & Related papers  (2025-10-02T06:25:10Z)
• Structured Cognitive Loop for Behavioral Intelligence in Large Language Model Agents [0.0]
  Existing frameworks often mix cognition, memory, and control in a single prompt, reducing coherence and predictability.<n>The Structured Cognitive Loop (SCL) is proposed as an alternative architecture that separates these functions.<n>SCL achieves an average task success rate of 86.3 percent, compared with 70.5 to 76.8 percent for baselines.
  arXiv  Detail & Related papers  (2025-09-23T17:43:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.