# Designing Skill-Compatible AI: Methodologies and Frameworks in Chess

arXiv: https://arxiv.org/abs/2405.05066 · HTML: https://mlsanity.com/paper/2405.05066/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 24 references that are in the map.
- First posted on arXiv 8 May 2024.

## Builds on (most cited first, 12 of 12)

- [Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model](https://mlsanity.com/paper/1911.08265/) (2019)
- [On the Utility of Learning about Humans for Human-AI Coordination](https://mlsanity.com/paper/1910.05789/) (2019)
- [The Hanabi Challenge: A New Frontier for AI Research](https://mlsanity.com/paper/1902.00506/) (2019)
- [Collaborating with Humans without Human Data](https://mlsanity.com/paper/2110.08176/) (2021)
- [Acquisition of Chess Knowledge in AlphaZero](https://mlsanity.com/paper/2111.09259/) (2021)
- [Aligning Superhuman AI with Human Behavior: Chess as a Model System](https://mlsanity.com/paper/2006.01855/) (2020)
- [Monte-Carlo Tree Search as Regularized Policy Optimization](https://mlsanity.com/paper/2007.12509/) (2020)
- [Modeling Strong and Human-Like Gameplay with KL-Regularized Search](https://mlsanity.com/paper/2112.07544/) (2021)
- [Human-Level Performance in No-Press Diplomacy via Equilibrium Search](https://mlsanity.com/paper/2010.02923/) (2020)
- [Chess AI: Competing Paradigms for Machine Intelligence](https://mlsanity.com/paper/2109.11602/) (2021)
- [Optimal Behavior Prior: Data-Efficient Human Models for Improved Human-AI Collaboration](https://mlsanity.com/paper/2211.01602/) (2022)
- [Assessing Human Error Against a Benchmark of Perfection](https://mlsanity.com/paper/1606.04956/) (2016)

## Built on by (most cited first, 10 of 10)

- [User Simulation in the Era of Generative AI: User Modeling, Synthetic Data Generation, and System Evaluation](https://mlsanity.com/paper/2501.04410/) (2025)
- [Student-Informed Teacher Training](https://mlsanity.com/paper/2412.09149/) (2024)
- [AI-Assisted Decision Making with Human Learning](https://mlsanity.com/paper/2502.13062/) (2025)
- [Chessformer: A Unified Architecture for Chess Modeling](https://mlsanity.com/paper/2605.19091/) (2026)
- [Designing Algorithmic Delegates: The Role of Indistinguishability in Human-AI Handoff](https://mlsanity.com/paper/2506.03102/) (2025)
- [Giving AI Personalities Leads to More Human-Like Reasoning](https://mlsanity.com/paper/2502.14155/) (2025)
- [Tandem Training for Language Models](https://mlsanity.com/paper/2510.13551/) (2025)
- [The Indispensable Role of User Simulation in the Pursuit of AGI](https://mlsanity.com/paper/2509.19456/) (2025)
- [Tandem Reinforcement Learning with Verifiable Rewards](https://mlsanity.com/paper/2606.28166/) (2026)
- [Discovering High-Quality Chess Puzzles with Offline Reinforcement Learning](https://mlsanity.com/paper/2608.14851/) (2026)

## Abstract (arXiv)

Powerful artificial intelligence systems are often used in settings where they must interact with agents that are computationally much weaker, for example when they work alongside humans or operate in complex environments where some tasks are handled by algorithms, heuristics, or other entities of varying computational power. For AI agents to successfully interact in these settings, however, achieving superhuman performance alone is not sufficient; they also need to account for suboptimal actions or idiosyncratic style from their less-skilled counterparts. We propose a formal evaluation framework for assessing the compatibility of near-optimal AI with interaction partners who may have much lower levels of skill; we use popular collaborative chess variants as model systems to study and develop AI agents that can successfully interact with lower-skill entities. Traditional chess engines designed to output near-optimal moves prove to be inadequate partners when paired with engines of various lower skill levels in this domain, as they are not designed to consider the presence of other agents. We contribute three methodologies to explicitly create skill-compatible AI agents in complex decision-making settings, and two chess game frameworks designed to foster collaboration between powerful AI agents and less-skilled partners. On these frameworks, our agents outperform state-of-the-art chess AI (based on AlphaZero) despite being weaker in conventional chess, demonstrating that skill-compatibility is a tangible trait that is qualitatively and measurably distinct from raw performance. Our evaluations further explore and clarify the mechanisms by which our agents achieve skill-compatibility.