English

Recursive Knowledge Synthesis for Multi-LLM Systems: Stability Analysis and Tri-Agent Audit Framework

Computation and Language 2026-01-15 v1

Abstract

This paper presents a tri-agent cross-validation framework for analyzing stability and explainability in multi-model large language systems. The architecture integrates three heterogeneous LLMs-used for semantic generation, analytical consistency checking, and transparency auditing-into a recursive interaction cycle. This design induces Recursive Knowledge Synthesis (RKS), where intermediate representations are continuously refined through mutually constraining transformations irreducible to single-model behavior. Across 47 controlled trials using public-access LLM deployments (October 2025), we evaluated system stability via four metrics: Reflex Reliability Score (RRS), Transparency Score (TS), Deviation Detection Rate (DDR), and Correction Success Rate (CSR). The system achieved mean RRS = 0.78+-0.06 and maintained TS >= 0.8 in about 68% of trials. Approximately 89% of trials converged, supporting the theoretical prediction that transparency auditing acts as a contraction operator within the composite validation mapping. The contributions are threefold: (1) a structured tri-agent framework for coordinated reasoning across heterogeneous LLMs, (2) a formal RKS model grounded in fixed-point theory, and (3) empirical evaluation of inter-model stability under realistic, non-API public-access conditions. These results provide initial empirical evidence that a safety-preserving, humansupervised multi-LLM architecture can achieve stable recursive knowledge synthesis in realistic, publicly deployed environments.

Keywords

Cite

@article{arxiv.2601.08839,
  title  = {Recursive Knowledge Synthesis for Multi-LLM Systems: Stability Analysis and Tri-Agent Audit Framework},
  author = {Toshiyuki Shigemura},
  journal= {arXiv preprint arXiv:2601.08839},
  year   = {2026}
}

Comments

25 pages, 9 figures. Pilot feasibility study using public-access large language models without API-level orchestration

R2 v1 2026-07-01T09:03:15.518Z