cs.AINov 13, 2026

TReC: Evaluating Move-Induced State Changes in Instruction-Conditioned Go

Authors: Zhuangsheng Li, Yunhan Zhang, Dailin Li, Qingxian Yu, Yu Wu, Youqi Song, Bangyuan He

Organizations: University of California, San Diego · University of Melbourne · University of Virginia · Shanghai Jiao Tong University · 

Abstract

When a Go model predicts a move different from the expert's, coordinate distance measures how far the prediction lands from the reference. We introduce Transition Representation Consistency (TReC) to compare how the two moves change a board-state embedding. Both moves are executed from the same position under the game rules, and TReC is the cosine similarity between the two resulting representation changes. In experiments with a frozen KataGo network on 680 mid-to-late-game positions from five games, the gap between the highest and lowest candidate per position has a median of 0.01 to 0.08 for the direct successor-state cosine and 0.88 to 1.33 for TReC, depending on the evaluator layer. TReC follows coordinate distance only weakly: the rank correlation between a candidate's distance to the reference and its TReC, computed within each position, has a median of -0.19 over these positions.

Figures & tables

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Chess-World-Model: A 10M-Game Benchmark for Exact State Tracking from Chess Move Sequences

    May 28, 2026Benjamin Walker, Terry LyonsRecurrent Neural NetworksState Tracking

  2. CoToan: Executable Rules and a Representation Contract for Reproducible Game AI Evaluation

    Oct 29, 2026Ha-Thanh NguyenAI Agent EvaluationGame-Playing Agents