--- title: Self-Evolving AI Agents Are Here and They Write Their... description: A new research paper called Autogenesis introduces a framework where AI agents negotiate and evolve their own collaboration protocols through an evolutionary... canonical: https://daily.dev/posts/self-evolving-ai-agents-are-here-and-they-write-their-own-protocols--zunjdm5gf twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Self-Evolving AI Agents Are Here and They Write Their Own Protocols ! | daily.dev og:description: A new research paper called Autogenesis introduces a framework where AI agents negotiate and evolve their own collaboration protocols through an evolutionary... og:url: https://daily.dev/posts/self-evolving-ai-agents-are-here-and-they-write-their-own-protocols--zunjdm5gf og:image: https://api.daily.dev/og/posts/zunJDM5GF.png og:image:alt: Self-Evolving AI Agents Are Here and They Write Their Own Protocols ! og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Self-Evolving AI Agents Are Here and They Write Their Own Protocols ! **[InfoSec Write-ups](https://daily.dev/sources/infosecwriteups)** · 10 min read · 0 upvotes · 0 comments ## Summary A new research paper called Autogenesis introduces a framework where AI agents negotiate and evolve their own collaboration protocols through an evolutionary process. Unlike fixed multi-agent topologies, Autogenesis has two layers: an execution layer and an evolution layer that modifies agent roles, communication patterns, and decision protocols based on performance metrics. From a security perspective, this creates three major concerns: auditability breaks down because evolved protocols emerge from optimization rather than design; a new protocol injection attack surface exists where adversaries can poison the evolution process by manipulating training tasks; and existing compliance frameworks (NIST AI RMF, OWASP LLM Top 10) don't address protocol-level poisoning. Security teams are advised to monitor protocol-level changes, constrain the evolution space with invariants, version and audit protocol history, and red-team the evolution process itself. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Medium](https://daily.dev/posts/medium-t4qlwxuej) · Medium · 0 upvotes · 0 comments - [AI Agents Can Fight. Anthropic’s Report Reveals the Missing Layer in Multi-Agent Architecture.](https://daily.dev/posts/ai-agents-can-fight-anthropic-s-report-reveals-the-missing-layer-in-multi-agent-architecture--bvm3irkcv) · gitconnected · 1 upvotes · 0 comments - [Agentic Autonomy Levels](https://daily.dev/posts/agentic-autonomy-levels-aklc8folj) · Addy Osmani · 4 upvotes · 1 comments --- Tags: [#security](https://daily.dev/tags/security), [#ai-agents](https://daily.dev/tags/ai-agents), [#ai-security](https://daily.dev/tags/ai-security) [View this post on daily.dev](https://daily.dev/posts/self-evolving-ai-agents-are-here-and-they-write-their-own-protocols--zunjdm5gf) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Self-Evolving AI Agents Are Here and They Write Their Own Protocols !","url":"https://daily.dev/posts/self-evolving-ai-agents-are-here-and-they-write-their-own-protocols--zunjdm5gf","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/self-evolving-ai-agents-are-here-and-they-write-their-own-protocols--zunjdm5gf"},"datePublished":"2026-04-21T06:51:59.567Z","dateModified":"2026-04-21T06:52:28.282Z","description":"A new research paper called Autogenesis introduces a framework where AI agents negotiate and evolve their own collaboration protocols through an evolutionary...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/51bf1ad8f354b3fc43a15d7e79e0c35e?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/51bf1ad8f354b3fc43a15d7e79e0c35e?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"InfoSec Write-ups","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"InfoSec Write-ups","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/f0dc21b5bbfd46fda36f7b4b53dd1705","url":"https://daily.dev/sources/infosecwriteups"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/self-evolving-ai-agents-are-here-and-they-write-their-own-protocols--zunjdm5gf","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"security,ai-agents,ai-security","timeRequired":"PT10M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"InfoSec Write-ups","item":"https://daily.dev/sources/infosecwriteups"},{"@type":"ListItem","position":3,"name":"Self-Evolving AI Agents Are Here and They Write Their Own Protocols !"}]} ```