# Value-Preserving Architectures for Agentic AI Systems

arXiv: https://arxiv.org/abs/2609.03920 · HTML: https://mlsanity.com/paper/2609.03920/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 15 of its 40 references that are in the map.
- First posted on arXiv 3 Sep 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 15 of 15)

- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Harms from Increasingly Agentic Algorithmic Systems](https://mlsanity.com/paper/2302.10329/) (2023)
- [Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration](https://mlsanity.com/paper/2406.15951/) (2024)
- [Towards Implicit Bias Detection and Mitigation in Multi-Agent LLM Interactions](https://mlsanity.com/paper/2410.02584/) (2024)
- [Agent Design Pattern Catalogue: A Collection of Architectural Patterns for Foundation Model based Agents](https://mlsanity.com/paper/2405.10467/) (2024)
- [The Attack and Defense Landscape of Agentic AI: A Comprehensive Survey](https://mlsanity.com/paper/2603.11088/) (2026)
- [Plurals: A System for Guiding LLMs Via Simulated Social Ensembles](https://mlsanity.com/paper/2409.17213/) (2024)
- [1-2-3 Check: Enhancing Contextual Privacy in LLM via Multi-Agent Reasoning](https://mlsanity.com/paper/2508.07667/) (2025)
- [The Orchestration of Multi-Agent Systems: Architectures, Protocols, and Enterprise Adoption](https://mlsanity.com/paper/2601.13671/) (2026)
- [Swiss Cheese Model for AI Safety: A Taxonomy and Reference Architecture for Multi-Layered Guardrails of Foundation Model Based Agents](https://mlsanity.com/paper/2408.02205/) (2024)
- [Towards a Roadmap on Software Engineering for Responsible AI](https://mlsanity.com/paper/2203.08594/) (2022)
- [Dynamic fairness-aware recommendation through multi-agent social choice](https://mlsanity.com/paper/2303.00968/) (2023)
- [Operationalizing Human Values in Software Engineering: A Survey](https://mlsanity.com/paper/2108.05624/) (2021)

## Abstract (arXiv)

The emergence of agentic AI and LLM-based multi-agent systems (MAS) presents unprecedented opportunities for automating complex tasks, while simultaneously raising critical concerns about the preservation of fundamental human-centered values, such as privacy, fairness, and safety. Although software engineering has traditionally focused on functional correctness, the adoption of LLMs and AI agents into complex socio-technical systems has intensified the need for responsible software engineering and robust value alignment. In MAS, architectural design decisions, such as coordination mechanisms, communication protocols, and system topologies, play a central role in shaping system behavior and the outcomes they produce. This paper argues that architectural choices influence not only the functionality and performance of MAS but can also promote value-oriented system behavior. Therefore, we investigate how different architectural designs support different human-centered values, discussing the following value-preserving architectural patterns: (i) a privacy-aware architecture with a federated topology, (ii) a distributed architecture to promote pluralism and diversity, and (iii) a guard-agent architecture to detect and mitigate unfairness. Finally, we introduce representative use cases to illustrate the proposed architectures in real-world scenarios. By linking architectural design with human-centered values, this work lays the foundation for a unified set of architectural patterns and guidelines towards the design of trustworthy MAS.