v2 · February 2026 · NeurIPS Submission

EthicaAI
Beyond Homo Economicus

Computational Verification of Sen's Meta-Ranking Theory
via Multi-Agent Reinforcement Learning

Yesol Heo · Neo Genesis Research

Explore 70 Figures ↓ Zenodo DOI ↗ GitHub ↗ Risk Governance Guide

At a Glance

560+ experiments. 70 figures.

0
Experiment Runs
0
Figures
0
Environments
0
Research Stages
0
Max Agents
p=.0023
HAC Robust SE
EthicaAI formalizes Amartya Sen's "Meta-Ranking" theory — preferences over preferences — as a dynamic mechanism in Multi-Agent Reinforcement Learning. We demonstrate that Situational Commitment — morality conditional on survival — is the only Evolutionarily Stable Strategy across 4 environments, 7 SVO conditions, and up to 1,000 agents.
Search focus: this research surface now routes AI ethics, AI compliance evaluation, and AI risk governance queries into two dedicated guides. Use the governance guide for policy and risk framing, and the compliance guide for evidence, audit criteria, and model evaluation questions.

AI ethics risk governance guide  ·  AI compliance evaluation guide

Key Findings

What we discovered

1

Dynamic meta-ranking enhances collective welfare significantly

p=0.0003 · Cohen's f²=0.40
2

Agents exhibit emergent role specialization — Cleaners vs Eaters

σ divergence p<0.0001
3

Only "Situational Commitment" survives as Evolutionarily Stable Strategy

~12% of population · 200-gen
4

Individualist SVO best matches human PGG behavioral data

Wasserstein Distance = 0.053
5

SVO rotation accounts for majority of total causal effect

86% · full factorial 2³
6

Human-AI behavioral alignment maintained across all conditions

WD < 0.2 all conditions
7

Byzantine robustness maintained with up to 50% adversarial agents

Up to 50% adversaries
8

Scale invariance verified from small groups to large populations

20 → 1,000 agents · ATE ±0.03

Interactive Playground

Try the simulation

Adjust SVO angle and toggle Meta-Ranking to see how agent cooperation changes in real time

Selfish 0° Prosocial 45° Altruist 90°
METRICS
Wasserstein D
—
Avg Contribution
—
Final λ
—
Contribution Rate
● Meta-Ranking ● Baseline ● Human

Research Journey

Seven stages

Stage 1: Core PGG
7 SVO conditions, causal inference framework, baseline experiments
Stage 2: Extended
Mixed-SVO populations, communication channels, continuous action spaces
Stage 3: Cross-Environment
Validation across IPD, PGG, Harvest — evolutionary dynamics
Stage 4: Human Alignment
Behavioral alignment with human PGG data, 100-agent scalability
Stage 5: MAPPO
Partial observability, LLM comparison, multi-resource environments
Stage 6: Applications
Vaccine allocation, AI governance, human-AI interaction scenarios
Stage 7: Robustness Final
Byzantine robustness, Moran process, GNN architecture, policy implications

Governance surfaces

AI risk, compliance, and safety entry points

Dedicated pages for global users searching for AI governance, model risk, compliance readiness, safety evaluation, documentation, and incident response workflows.

AI governance checklist Model risk management checklist AI compliance audit readiness EU AI Act readiness checklist NIST AI RMF checklist High-risk AI system checklist AI safety evaluation checklist AI risk register template AI model validation checklist AI documentation checklist AI incident response playbook

Cite This Work

Use in your research

@article{heo2026ethicaai, title={EthicaAI: Beyond Homo Economicus -- Computational Verification of Sen's Meta-Ranking Theory via Multi-Agent RL}, author={Heo, Yesol}, year={2026}, url={https://ethica.neogenesis.app}, doi={10.5281/zenodo.18637742} }
Zenodo DOI ↗ GitHub ↗