FRACTAL：具备形式化通信、收敛与深度边界的自相似多智能体编排架构

View PDF HTML (experimental)

Abstract:We present FRACTAL, a self-similar multi-agent architecture for recursive goal decomposition, in which the same five-component organizational pattern -- Orchestrator, Ensemble, Knowledge Ledger, Decision Maker, Meta-Observer -- recurs at every level of a decomposition tree. We make four formal contributions: (1) a communication bound showing intra-node cost is linear in ensemble size and round count (O(kr)) under a two-phase blind-proposal/stress-test protocol, versus quadratic cost for free-form debate, with an explicit, stated assumption on fixed evaluator count; (2) a two-mode orchestration criterion separating generative and evaluative phases via a measurable diversity-saturation threshold; (3) a supermajority convergence guarantee with explicit probability bounds at stated agreement levels, and a formal depth bound under an operationalized goal-complexity measure; (4) a Bayesian inter-layer escalation mechanism unifying hysteresis and contract-breach signaling under one posterior update. We illustrate the architecture's execution qualitatively on a worked example and a multi-layer case study; we do not report quantitative performance claims in this paper, and we explicitly discuss the formal and inductive-bias limitations of the model, including an unimplemented but architecture-compatible direction toward bounded self-improvement. We use "fractal" as an architectural metaphor for self-similarity, not a measured mathematical property. Empirical validation of the architecture's comparative performance is left to future work.

Subjects:	Artificial Intelligence (cs.AI)
Cite as:	arXiv:2610.22561 [cs.AI]
	(or arXiv:2610.22561v1 [cs.AI] for this version)
	https://doi.org/10.48550/arXiv.2610.22561 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Ohad Dan [view email]
[v1] Thu, 15 Oct 2026 19:02:50 UTC (554 KB)