三模型协作实现大模型系统稳定推理与可解释性验证。
Recursive Knowledge Synthesis for Multi-LLM Systems: Stability Analysis and Tri-Agent Audit Framework
- 三模型递归交互，通过互相约束实现知识持续优化。
- 平均可靠性达0.78，透明度得分在68%试验中保持≥0.8。
- 适用于需安全可控的多模型系统，如智能决策与审计场景。
本文提出一种三代理交叉验证框架，用于分析多模型大语言系统中的稳定性与可解释性。该架构整合三种异构LLM——语义生成、分析一致性校验与透明度审计——形成递归交互循环，催生递归知识合成（RKS），使中间表示在相互制约的变换中持续优化，其行为无法还原为单一模型表现。基于2025年10月公开部署的LLM进行47次受控实验，采用四项指标评估系统稳定性：反射可靠性分数（RRS）、透明度得分（TS）、偏差检测率（DDR）与纠错成功率（CSR）。系统平均RRS为0.78±0.06，在约68%试验中维持TS≥0.8；约89%试验实现收敛，支持理论预测——透明度审计在复合验证映射中起收缩算子作用。贡献包括：(1) 面向异构LLM协同推理的结构化三代理框架；(2) 基于不动点理论的RKS形式化模型；(3) 在真实、非API公开访问条件下对多模型间稳定性的实证评估。结果初步证明，具备人类监督的安全增强型多模型架构可在真实公开环境中实现稳定的递归知识合成。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。