Modular Speaker Architecture: A Framework for Sustaining Responsibility and Contextual Integrity in Multi-Agent AI Communication

TL;DR

This paper introduces the Modular Speaker Architecture (MSA), a framework that enhances multi-agent AI communication by explicitly managing responsibility and context, leading to more coherent and interpretable interactions.

Contribution

The paper presents MSA, a novel modular framework for role tracking, responsibility, and contextual integrity in multi-agent AI communication, with a prototype language and API.

Findings

MSA maintains interaction structure without affective signals.

MSA improves responsibility and context stability in multi-agent dialogues.

Structural metrics confirm MSA's effectiveness in preserving communication coherence.

Abstract

Sustaining coherent, role-aware communication across multi-agent systems remains a foundational challenge in AI. Current frameworks often lack explicit mechanisms for speaker responsibility, leading to context drift, alignment instability, and degraded interpretability over time. We propose the Modular Speaker Architecture (MSA), a framework that decomposes speaker behavior into modular components for role tracking, responsibility continuity, and contextual coherence. Grounded in high-context human-AI dialogues, MSA includes three core modules: a Speaker Role Module, a Responsibility Chain Tracker, and a Contextual Integrity Validator. We evaluate MSA through annotated case studies and introduce structural metrics-pragmatic consistency, responsibility flow, and context stability-quantified via manual and automatic scoring and bootstrapped statistical analysis. Our results show that MSA reliably maintains interaction structure without reliance on affective signals or surface-level heuristics. We further implement a prototype configuration language (G-Code) and modular API to support MSA deployment in dynamic multi-agent scenarios.