# Self-Evolving Coordination Protocol in Multi-Agent AI Systems: An Exploratory Systems Feasibility Study

arXiv: https://arxiv.org/abs/2602.02170 · HTML: https://mlsanity.com/paper/2602.02170/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 25 references that are in the map.
- First posted on arXiv 2 Feb 2026.

## Builds on (most cited first, 5 of 5)

- [Multi-Agent Coordination across Diverse Applications: A Survey](https://mlsanity.com/paper/2502.14743/) (2025)
- [Rethinking the Reliability of Multi-agent System: A Perspective from Byzantine Fault Tolerance](https://mlsanity.com/paper/2511.10400/) (2025)
- [Byzantine Fault-Tolerant Multi-Agent System for Healthcare: A Gossip Protocol Approach to Secure Medical Message Propagation](https://mlsanity.com/paper/2512.17913/) (2025)
- [FnF-BFT: Exploring Performance Limits of BFT Protocols](https://mlsanity.com/paper/2009.02235/) (2020)
- [BigBFT: A Multileader Byzantine Fault Tolerance Protocol for High Throughput](https://mlsanity.com/paper/2109.12664/) (2021)

## Built on by (most cited first, 1 of 1)

- [Towards Selection as Power: Bounding Decision Authority in Autonomous Agents](https://mlsanity.com/paper/2602.14606/) (2026)

## Abstract (arXiv)

Contemporary multi-agent systems increasingly rely on internal coordination mechanisms to combine, arbitrate, or constrain the outputs of heterogeneous components. In safety-critical and regulated domains such as finance, these mechanisms must satisfy strict formal requirements, remain auditable, and operate within explicitly bounded limits. Coordination logic therefore functions as a governance layer rather than an optimization heuristic. This paper presents an exploratory systems feasibility study of Self-Evolving Coordination Protocols (SECP): coordination protocols that permit limited, externally validated self-modification while preserving fixed formal invariants. We study a controlled proof-of-concept setting in which six fixed Byzantine consensus protocol proposals are evaluated by six specialized decision modules. All coordination regimes operate under identical hard constraints, including Byzantine fault tolerance (f < n/3), O(n2) message complexity, complete non-statistical safety and liveness arguments, and bounded explainability. Four coordination regimes are compared in a single-shot design: unanimous hard veto, weighted scalar aggregation, SECP v1.0 (an agent-designed non-scalar protocol), and SECP v2.0 (the result of one governed modification). Outcomes are evaluated using a single metric, proposal coverage, defined as the number of proposals accepted. A single recursive modification increased coverage from two to three accepted proposals while preserving all declared invariants. The study makes no claims regarding statistical significance, optimality, convergence, or learning. Its contribution is architectural: it demonstrates that bounded self-modification of coordination protocols is technically implementable, auditable, and analyzable under explicit formal constraints, establishing a foundation for governed multi-agent systems.