Knowledge Compounding: An Empirical Economic Analysis of Self-Evolving Knowledge Wikis under the Agentic ROI Framework

TL;DR

This paper empirically demonstrates that integrating a structured knowledge layer in LLM agents significantly reduces token consumption and costs through knowledge compounding, validated by experiments on Qing Claw.

Contribution

It introduces the concept of knowledge compounding, proposes a dynamic Agentic ROI model, and provides a minimal C# implementation of an industrial-grade LLM wiki system.

Findings

Cumulative token consumption reduced by 84.6% under the compounding regime.

Projected savings of up to 81.3% over 30 days with high topic concentration.

Identified microeconomic mechanisms driving the knowledge compounding effect.

Abstract

Building on the Agentic ROI framework proposed by Liu et al. (2026), this paper introduces knowledge compounding as a new measurable concept in the empirical economics of LLM agents and validates it through a controlled four-query experiment on Qing Claw, an industrial-grade C# reimplementation of the OpenClaw multi-agent framework. Our central theoretical claim is that the cost term in the original Agentic ROI equation contains an unexamined assumption -- that the cost of each task is mutually independent. This assumption holds under the traditional retrieval-augmented generation (RAG) paradigm but breaks down once a persistent, structured knowledge layer is introduced. We propose a dynamic Agentic ROI model in which cost is treated as a time-varying function Cost(t) governed by a knowledge-base coverage rate H(t). Empirical results from four sequential queries on the same domain yield a cumulative token consumption of 47K under the compounding regime versus 305K under a matched RAG baseline -- a savings of 84.6%. Calibrated 30-day projections indicate cumulative savings of 53.7% under medium topic concentration and 81.3% under high concentration, with the gap widening monotonically over time. We further identify three microeconomic mechanisms underlying the compounding effect: (i) one-time INGEST amortized over N retrievals, (ii) auto-feedback of high-value answers into synthesis pages, and (iii) write-back of external search results into entity pages. The theoretical contribution of this paper is a recategorization of LLM tokens from consumables to capital goods, shifting the economic discussion from static marginal cost analysis to dynamic capital accumulation. The engineering contribution is a minimal reproducible implementation in approximately 200 lines of C#, which we believe is the first complete industrial-grade reference implementation of Karpathy's (2026) LLM Wiki paradigm.