# Modeling the Centaur: Human-Machine Synergy in Sequential Decision Making

arXiv: https://arxiv.org/abs/2412.18593 · HTML: https://mlsanity.com/paper/2412.18593/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Dec 2024.

## Built on by (most cited first, 2 of 2)

- [Ailed: A Psyche-Driven Chess Engine with Dynamic Emotional Modulation](https://mlsanity.com/paper/2603.05352/) (2026)
- [Idempotent Equilibrium Analysis of Hybrid Workflow Allocation: A Mathematical Schema for Future Work](https://mlsanity.com/paper/2508.01323/) (2025)

## Abstract (arXiv)

The field of collective intelligence studies how teams can achieve better results than any of the team members alone. The special case of human-machine teams carries unique challenges in this regard. For example, human teams often achieve synergy by communicating to discover their relative advantages, which is not an option if the team partner is an unexplainable deep neural network. Between 2005-2008 a set of "freestyle" chess tournaments were held, in which human-machine teams known as "centaurs", outperformed the best humans and best machines alone. Centaur players reported that they identified relative advantages between themselves and their chess program, even though the program was superhuman. Inspired by this and leveraging recent open-source models, we study human-machine like teams in chess. A human behavioral clone ("Maia") and a pure self-play RL-trained chess engine ("Leela") were composed into a team using a Mixture of Experts (MoE) architecture. By directing our research question at the selection mechanism of the MoE, we could isolate the issue of extracting relative advantages without knowledge sharing. We show that in principle, there is high potential for synergy between human and machine in a complex sequential decision environment such as chess. Furthermore, we show that an expert can identify only a small part of these relative advantages, and that the contribution of its subject matter expertise in doing so saturates quickly. This is probably due to the "curse of knowledge" phenomenon. We also train a network to recognize relative advantages using reinforcement learning, without chess expertise, and it outdoes the expert. Our experiments are repeated in asymmetric teams, in which identifying relative advantages is more challenging. Our findings contribute to the study of collective intelligence and human-centric AI.