CTHA: Constrained Temporal Hierarchical Architecture for Stable Multi-Agent LLM Systems

TL;DR

The paper introduces CTHA, a framework that enhances stability and scalability in multi-agent LLM systems with temporal hierarchies by enforcing structured communication and decision constraints.

Contribution

It proposes a novel constrained hierarchical architecture that formalizes inter-layer communication and decision-making, improving stability and scalability in multi-agent systems.

Findings

47% reduction in failure cascades

2.3x improvement in sample efficiency

Superior scalability over baselines

Abstract

Recently, multi-time-scale agent architectures have extended the ubiquitous single-loop paradigm by introducing temporal hierarchies with distinct cognitive layers. While yielding substantial performance gains, this diversification fundamentally compromises the coordination stability intrinsic to unified agent systems, which causes severe inter-layer conflicts, unbounded error propagation, and restricted scalability. To address these challenges, we propose Constrained Temporal Hierarchical Architecture (CTHA), a general framework that projects the inter-layer communication space onto structured manifolds to restore coordination stability, while incorporating principled arbitration mechanisms to ensure coherent decision-making. Specifically, CTHA enforces three key constraints: (1) Message Contract Constraints that formalize information flow between layers via typed summary, plan, and policy packets; (2) Authority Manifold Constraints that bound each layer's decision space according to its temporal scope; and (3) Arbiter Resolution Constraints that guarantee conflict-free composition of multi-layer decisions. Empirical experiments demonstrate that CTHA is effective for complex task execution at scale, offering 47% reduction in failure cascades, 2.3x improvement in sample efficiency, and superior scalability compared to unconstrained hierarchical baselines. We anticipate that CTHA, as a principled extension of temporal hierarchies, will contribute to a deeper understanding of multi-agent coordination and suggest promising directions for the evolution of robust autonomous systems.