Chess research maps how humans and AI reason strategically
What Counts as Strategic Reasoning? A Systematic Mapping of Chess Research on Humans, Engines, and Language Models
Artificial Intelligence
Summary
Chess is often used to study how people and computers think ahead and make decisions. The authors looked at many recent studies involving humans, classic chess engines, newer AI systems, and language models. They found most research focuses on understanding the chess situation and choosing moves, but less on deeper planning, explaining decisions, or teamwork between humans and AI. Their work helps show where chess can teach us about strategic thinking and how future research might better combine humans and AI.
What this means in practice
- •For game ai developers: Use the mapping to guide chess AI design focusing beyond move selection to include explicit planning and explanation capabilities.
- •For human-computer interaction teams: Design better chess tools that integrate human and AI decision-making by addressing gaps in collaboration and explainability shown by the map.
A survey. It maps existing work.
Authors
Paolo Ciancarini, Remo Pareschi
Abstract
Chess has long served as a model domain for studying search, expertise, decision-making, and artificial intelligence. The emergence of large language models (LLMs) has renewed the relevance of chess as a controlled environment for investigating strategic reasoning and comparing human and artificial decision-making. We present a systematic mapping study of recent research spanning human players, classical chess engines, neural and reinforcement-learning systems, LLMs, and hybrid approaches. The final map comprises 84 core study families, classified according to agent type, strategic-reasoning stages, and evaluation dimensions. The map reveals a literature strongly concentrated on situation assessment, evaluation, and action selection, while explicit planning, explanation, metacognition, and human--AI collaboration remain less explored. LLM research places particular emphasis on state representation and generalization, whereas grounded explanation appears more frequently in hybrid approaches combining language models with engines, expert knowledge, or other external structures. Two distinctions emerge that the map aggregates rather than resolves: hybrid systems differ in where and when heterogeneous capabilities combine, and evaluations that show improved human performance do not thereby establish human--AI synergy. We propose both as extensions of the mapping framework. We argue that chess provides a useful bridge between cognitive and computational perspectives on strategic reasoning, and identify explicit planning, grounded and faithful explanation, metacognitive calibration, and human--AI complementarity as directions for future research.