# HADA: Human-AI Agent Decision Alignment Architecture

arXiv: https://arxiv.org/abs/2506.04253 · HTML: https://mlsanity.com/paper/2506.04253/

## Key facts

- Cited by 1 papers in the map (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 22 of its 34 references that are in the map.
- First posted on arXiv 1 Jun 2025.

## 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, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [A Comprehensive Overview of Large Language Models](https://mlsanity.com/paper/2307.06435/) (2023)
- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims](https://mlsanity.com/paper/2004.07213/) (2020)
- [Foundation Models for Decision Making: Problems, Methods, and Opportunities](https://mlsanity.com/paper/2303.04129/) (2023)
- [The Off-Switch Game](https://mlsanity.com/paper/1611.08219/) (2016)
- [A Survey of AI Agent Protocols](https://mlsanity.com/paper/2504.16736/) (2025)
- [Large Language Models Pass the Turing Test](https://mlsanity.com/paper/2503.23674/) (2025)
- [Design Science Research Process: A Model for Producing and Presenting Information Systems Research](https://mlsanity.com/paper/2006.02763/) (2020)

## Built on by (most cited first, 1 of 1)

- [Multi-level Value Alignment in Agentic AI Systems: Survey and Perspectives](https://mlsanity.com/paper/2506.09656/) (2025)

## Abstract (arXiv)

We present HADA (Human-AI Agent Decision Alignment), a protocol- and framework agnostic reference architecture that keeps both large language model (LLM) agents and legacy algorithms aligned with organizational targets and values. HADA wraps any algorithm or LLM in role-specific stakeholder agents -- business, data-science, audit, ethics, and customer -- each exposing conversational APIs so that technical and non-technical actors can query, steer, audit, or contest every decision across strategic, tactical, and real-time horizons. Alignment objectives, KPIs, and value constraints are expressed in natural language and are continuously propagated, logged, and versioned while thousands of heterogeneous agents run on different orchestration stacks. A cloud-native proof of concept packages a production credit-scoring model (getLoanDecision) and deploys it on Docker/Kubernetes/Python; five scripted retail-bank scenarios show how target changes, parameter tweaks, explanation requests, and ethics triggers flow end to end through the architecture. Evaluation followed the Design-Science Research Methodology. Walkthrough observation and log inspection demonstrated complete coverage of six predefined objectives: every role could invoke conversational control, trace KPIs and value constraints, detect and mitigate ZIP-code bias, and reproduce full decision lineage, independent of the underlying LLM or agent library. Contributions: (1) an open-source HADA architecture, (2) a mid-range design theory for human-AI alignment in multi-agent systems, and (3) empirical evidence that framework-agnostic, protocol-compliant stakeholder agents improve accuracy, transparency, and ethical compliance in real-world decision pipelines.