AI 에이전트가 어떻게 협력할지 예측하는 실험

[Sitemap](https://pub.towardsai.net/sitemap/sitemap.xml) [Open in app](https://play.google.com/store/apps/details?id=com.medium.reader&referrer=utm_source%3DmobileNavBar&source=post_page---top_nav_layout_nav-----------------------------------------) Sign up [Sign in](https://medium.com/m/signin?operation=login&redirect=https%3A%2F%2Fpub.towardsai.net%2Finformation-topology-in-multi-agent-systems-cb925c5b86d9&source=post_page---top_nav_layout_nav-----------------------global_nav------------------) [Medium Logo](https://medium.com/?source=post_page---top_nav_layout_nav-----------------------------------------) Get app [](https://medium.com/m/signin?operation=register&redirect=https%3A%2F%2Fmedium.com%2Fnew-story&source=---top_nav_layout_nav-----------------------new_post_topnav------------------) [Search](https://medium.com/search?source=post_page---top_nav_layout_nav-----------------------------------------) Sign up [Sign in](https://medium.com/m/signin?operation=login&redirect=https%3A%2F%2Fpub.towardsai.net%2Finformation-topology-in-multi-agent-systems-cb925c5b86d9&source=post_page---top_nav_layout_nav-----------------------global_nav------------------)  ## [Towards AI](https://pub.towardsai.net/?source=post_page---publication_nav-98111c9905da-cb925c5b86d9---------------------------------------) · Follow publication [](https://pub.towardsai.net/?source=post_page---post_publication_sidebar-98111c9905da-cb925c5b86d9---------------------------------------) We build Enterprise AI. We teach what we learn. Join 100K+ AI practitioners on Towards AI Academy. Free: 6-day Agentic AI Engineering Email Guide: Follow publication # Information Topology in Multi-Agent Systems: as a Behavioral Parameter ## _A game theory experiment with controlled transparency on AI agents, the multi-agent orchestration platform that made it possible, and thoughts on what should agents know when designing workflows._ [](https://medium.com/@eren.karatas?source=post_page---byline--cb925c5b86d9---------------------------------------) [Eren Karatas](https://medium.com/@eren.karatas?source=post_page---byline--cb925c5b86d9---------------------------------------) 10 min read · Mar 7, 2026 [](https://medium.com/m/signin?actionUrl=https%3A%2F%2Fmedium.com%2F_%2Fvote%2Ftowards-artificial-intelligence%2Fcb925c5b86d9&operation=register&redirect=https%3A%2F%2Fpub.towardsai.net%2Finformation-topology-in-multi-agent-systems-cb925c5b86d9&user=Eren+Karatas&userId=3c0b10cadad8&source=---header_actions--cb925c5b86d9---------------------clap_footer------------------) -- [](https://medium.com/m/signin?actionUrl=https%3A%2F%2Fmedium.com%2F_%2Fbookmark%2Fp%2Fcb925c5b86d9&operation=register&redirect=https%3A%2F%2Fpub.towardsai.net%2Finformation-topology-in-multi-agent-systems-cb925c5b86d9&source=---header_actions--cb925c5b86d9---------------------bookmark_footer------------------) [Listen](https://medium.com/m/signin?actionUrl=https%3A%2F%2Fmedium.com%2Fplans%3Fdimension%3Dpost_audio_button%26postId%3Dcb925c5b86d9&operation=register&redirect=https%3A%2F%2Fpub.towardsai.net%2Finformation-topology-in-multi-agent-systems-cb925c5b86d9&source=---header_actions--cb925c5b86d9---------------------post_audio_button------------------) Share In a multi-agent system, every agent operates under a set of constraints. Its instructions, its tools, its model. But there’s a parameter that gets far less attention: **Information topology** : who knows what about whom, and when. This article presents an agent orchestration platform where information flow between agents is a first-class infrastructure primitive, and a controlled experiment that isolates it as the single independent variable. The experiment builds on iterated [Prisoner’s Dilemma research (Axelrod, 1980)](https://journals.sagepub.com/doi/10.1177/002200278002400101), with agents required to state their reasoning before every move. Press enter or click to view image in full size  Press enter or click to view image in full size  Agent orchestrator dashboard. ## The System The system that I develop is a multi-agent orchestration platform built on Python with the [Strands](https://strandsagents.com/latest/) SDK. Not a chatbot wrapper; a coordination layer. Multiple LLM agents run simultaneously in background threads, each with its own system prompt, conversation history, and tool access, coordinating through shared infrastructure and observable through UI. Press enter or click to view image in full size  The platform is built around six coordination pr