What question did this study set out to answer?

The aim is to define ethical constraints for agentic AI memory architectures focused on accountability and commitment.

April 13, 2026Open Access

SIP-AI-05: The Agentic Excretory Architecture Ethical Constraints for Persistent Action-Taking Systems

Key Points

The aim is to define ethical constraints for agentic AI memory architectures focused on accountability and commitment.
Introduces three extensions to excretory architecture: world model maintenance, action journal, and extended librarian function.
Establishes principles for how agentic AI should retain and manage action-outcome pairs and commitments.
Focuses on ethical implications rather than implementation logistics.
Identifies specific ethical failures of AI that forgets irreversible actions or evades accountability.
Highlights the importance of maintaining commitments in agentic systems to ensure ethical actions.

Abstract

This paper extends the Excretory Architecture (SIP-AI-03) to agentic AI systems — persistent, action-taking systems that build world models and execute consequential interventions. Three extensions are introduced: World Model Maintenance (ρ-bounded coherence checking for external reality representations), the Action Journal (reversibility-tagged retention with the Irreversibility Retention Principle), and the Extended Librarian Function (managing action-outcome pairs, commitment registers, and delegation records). The paper specifies ethical constraints that any agentic memory architecture must satisfy, rather than operational implementations. Core claim: an agent that forgets its irreversible actions, abandons its commitments, or evades accountability through delegation has failed ethically, regardless of operational efficiency.

Read Full Paperexternally

Ask AI

Helpful

Bookmark

View Full Paper