Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{184364,
        author = {Thenmozhi R and S.Shenbaga Vadivu and Joshua Lawrence},
        title = {Tacticus AI Chess Engine},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {4},
        pages = {1223-1228},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=184364},
        abstract = {A chess engine is a type of software designed to play chess automatically or assist human players in analyzing game positions. Its main function is to search through various moves and assess the resulting positions to determine the best move to make. Chess engines use a combination of complex algorithms and heuristics to evaluate positions, from basic material counts to advanced positional and tactical considerations. Tacticus is an AI chess engine that employs powerful hardware and sophisticated search techniques like alpha-beta pruning, transposition tables, and parallel processing to analyze billions of move sequences in seconds. At any given position, Tacticus uses a combination of min- max algorithms and alpha-beta pruning techniques to eliminate "useless" moves, i.e., moves that do not offer a clear objective advantage. For the remaining subtrees, Tacticus uses deep learning algorithms to evaluate the moves. The engine was trained on datasets consisting of previously played game exchanges and their moves, enabling it to predict paths with a high probability of winning. In the endgame, Tacticus switches to brute-forcing with Quiescence search, which is a technique that helps produce results that can almost guarantee success. Tacticus produces its output as a set of moves along with their predicted probability of winning. It can provide valuable analysis and feedback for players of all skill levels, from novice to grandmaster, and has revolutionized the way chess is played and studied. From theoretical calculations, Tacticus is estimated to have around 25% higher accuracy compared to other AI chess engines. This accuracy can be further improved by training Tacticus on more extensive and relevant datasets and by increasing the depth of the game tree traversed. Overall, Tacticus represents a significant breakthrough in AI chess engines and is likely to pave the way for further advancements in the field.},
        keywords = {ANN- Artificial Neural Network, CNN- Convolutional Neural Network},
        month = {September},
        }