A Multi-Agent Consensus Protocol for Stable Software Remodularization

TL;DR

This paper presents a novel multi-agent consensus protocol for software remodularization that balances structural cohesion and stability, with formal guarantees and promising preliminary experimental results.

Contribution

It introduces the Asymmetric Monotonic Concession Protocol (AMCP) for distributed negotiation in software clustering, ensuring Pareto-satisfactory partitions with formal proofs.

Findings

Protocol terminates with bounded concessions.

Matches state-of-the-art optimizers under loose stability.

Enforces strict stability constraints as a 'circuit breaker'.

Abstract

Automatic software remodularisation is typically cast as a single-objective optimization problem. While recent metaheuristics have improved search efficiency, real-world architecture recovery must reconcile the conflicting attributes of structural cohesion and evolutionary stability. We reframe software module clustering as a distributed consensus problem among autonomous agents. We introduce an Asymmetric Monotonic Concession Protocol (AMCP) that enables agents to negotiate decompositions that respect multi-attribute utility thresholds. We formally prove the protocol's termination, its bounded concession behaviour consistent with the Zeuthen Strategy under closed-instance conditions, and the local Pareto-satisfactoriness of the resulting partitions. Preliminary experiments on a synthetic benchmark and the Xwork Java framework confirm that our negotiated consensus matches state-of-the-art optimizers when stability budgets are loose, while acting as a "circuit breaker" to enforce strict stability constraints. Extended results on ten further systems, including comparisons with multi-objective evolutionary algorithms and multi-version chains, will be reported in a forthcoming full paper.