# Kiko: Programming Agents to Enact Interaction Protocols

arXiv: https://arxiv.org/abs/2606.26156 · HTML: https://mlsanity.com/paper/2606.26156/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jun 2026.

## Built on by (most cited first, 2 of 2)

- [Langshaw: Declarative Interaction Protocols Based on Sayso and Conflict](https://mlsanity.com/paper/2606.29601/) (2026)
- [A Comparative Study of MCP and A2A for Inter-Agent Coordination in LLM-Based Systems](https://mlsanity.com/paper/2607.23884/) (2026)

## Abstract (arXiv)

Realizing a multiagent system involves implementing member agents who interact based on a protocol while making decisions in a decentralized manner. Current programming models for agents offer poor abstractions for decision making and fail to adequately bridge an agent's internal decision logic with its public decisions. We present Kiko, a protocol-based programming model for agents. To implement an agent, a programmer writes one or more decision makers, each of which chooses from among a set of valid decisions and makes mutually compatible decisions on what messages to send. By completely abstracting away the underlying communication service and by supporting practical decision-making patterns, Kiko enables agent developers to focus on business logic. We provide an operational semantics for Kiko and establish that Kiko agents are protocol compliant and able to realize any protocol enactment.
