Tracking vs. Deciding: The Dual-Capability Bottleneck in Searchless Chess Transformers

• URL: http://arxiv.org/abs/2603.29761v1
• Date: Tue, 31 Mar 2026 14:01:39 GMT
• Title: Tracking vs. Deciding: The Dual-Capability Bottleneck in Searchless Chess Transformers
• Abstract summary: A human-like chess engine should mimic the style, errors, and consistency of a strong human player rather than maximize playing strength.<n>We show that training from move sequences alone forces a model to learn two capabilities: state tracking, which reconstructs the board from move history, and decision quality, which selects good moves from that reconstructed state.<n>We formalize this tension as a dual-capability bottleneck, P = min(T,Q), where overall performance is limited by the weaker capability.
• Score: 3.692740024498697
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: A human-like chess engine should mimic the style, errors, and consistency of a strong human player rather than maximize playing strength. We show that training from move sequences alone forces a model to learn two capabilities: state tracking, which reconstructs the board from move history, and decision quality, which selects good moves from that reconstructed state. These impose contradictory data requirements: low-rated games provide the diversity needed for tracking, while high-rated games provide the quality signal for decision learning. Removing low-rated data degrades performance. We formalize this tension as a dual-capability bottleneck, P <= min(T,Q), where overall performance is limited by the weaker capability. Guided by this view, we scale the model from 28M to 120M parameters to improve tracking, then introduce Elo-weighted training to improve decisions while preserving diversity. A 2 x 2 factorial ablation shows that scaling improves tracking, weighting improves decisions, and their combination is superadditive. Linear weighting works best, while overly aggressive weighting harms tracking despite lower validation loss. We also introduce a coverage-decay formula, t* = log(N/kcrit)/log b, as a reliability horizon for intra-game degeneration risk. Our final 120M-parameter model, without search, reached Lichess bullet 2570 over 253 rated games. On human move prediction it achieves 55.2% Top-1 accuracy, exceeding Maia-2 rapid and Maia-2 blitz. Unlike position-based methods, sequence input naturally encodes full game history, enabling history-dependent decisions that single-position models cannot exhibit.

Related papers

• CAST: Game Solvers as Turn-Level Teachers for LLM Agents [78.2379284312811]
  Training large language models (LLMs) to act in long-horizon games is a promising step toward generalist decision-making.<n>Denser process signals could supply this missing turn-level credit, but existing sources are hard to keep both cheap and accurate.<n>We propose CAST, which converts changes in a game solver's state value into solver advantages and injects them into RLVR as turn-level signals.
  arXiv  Detail & Related papers  (2026-07-28T05:39:01Z)
• SportD: Can VLMs Physically Strategize? [3.6356011518439684]
  SportD is a benchmark comprising 478 on-ball decisions from the 2022 FIFA World Cup.<n>Each model choice is evaluated against a possession-value model that estimates the action that most increases the attacking team's probability of scoring.<n>Across three frontier VLMs, the best selects the highest-valued action on 31.4% of events, compared with 38.9% for the professional players.
  arXiv  Detail & Related papers  (2026-07-16T06:30:26Z)
• Beyond the Current Observation: Evaluating Multimodal Large Language Models in Controllable Non-Markov Games [69.57330692969543]
  We introduce RNG-Bench, a benchmark suite designed to isolate a base model's ability to reconstruct past observations.<n>RNG-Bench includes two complementary games: Matching Pairs, where card identities briefly revealed at specific locations must later be recalled, and 3D Maze, where egocentric views must be integrated into a spatial map.<n>The hardest configurations require contexts of roughly 128K tokens and 350 image inputs per episode, and remain far from saturated by frontier MLLMs.
  arXiv  Detail & Related papers  (2026-06-17T17:59:34Z)
• ChessMimic: Per-Rating Transformer Models for Human Move, Clock, and Outcome Prediction in Online Blitz Chess [0.08460698440162888]
  ChessMimic is a system of three encoder-only transformers for move, thinking-time, and outcome prediction.<n>On a held-out month-wide slice of Lichess Rated Blitz games ChessMimic's human move prediction accuracy outperforms Maia-2 in every Elo band.<n>A public demo is at 1e4.ai and we release code, per-band weights, and the C++ data-filter pipeline code in GitHub.
  arXiv  Detail & Related papers  (2026-06-03T05:42:39Z)
• CPGRec+: A Balance-oriented Framework for Personalized Video Game Recommendations [26.80916834756631]
  We propose Preference-informed Edge Reweighting (PER) module and Preference-informed Representation Generation (PRG) module.<n>PER module assigns signed edge weights to qualitatively distinguish significant player interests and disinterests while then quantitatively measuring preference strength to mitigate over-smoothing in graph convolutions.<n>PRG module leverages LLMs to generate contextualized descriptions of games and players by reasoning personal preferences from comparing global and personal interests.
  arXiv  Detail & Related papers  (2026-04-16T03:25:18Z)
• Toward Personalized Darts Training: A Data-Driven Framework Based on Skeleton-Based Biomechanical Analysis and Motion Modeling [8.715408426200264]
  This paper presents a data-driven dart training assistance system.<n>The system creates a closed-loop framework spanning motion capture, feature modeling, and personalized feedback.<n>It can detect poor trunk stability, abnormal elbow displacement, and imbalanced velocity control, then provide targeted recommendations.
  arXiv  Detail & Related papers  (2026-04-01T16:51:30Z)
• MEMO: Memory-Augmented Model Context Optimization for Robust Multi-Turn Multi-Agent LLM Games [79.72300527041534]
  Multi-agent game evaluations often exhibit substantial run-to-run variance.<n>Small deviations compound across turns and are amplified by multi-agent coupling.<n>We address both instability and underperformance with MEMO (Memory-augmented MOdel context optimization), a self-play framework.
  arXiv  Detail & Related papers  (2026-03-09T23:36:32Z)
• Game-TARS: Pretrained Foundation Models for Scalable Generalist Multimodal Game Agents [56.25101378553328]
  We present Game-TARS, a generalist game agent trained with a unified, scalable action space anchored to human-aligned keyboard-mouse inputs.<n>Game-TARS is pre-trained on over 500B tokens with diverse trajectories and multimodal data.<n> Experiments show that Game-TARS achieves about 2 times the success rate over the previous sota model on open-world Minecraft tasks.
  arXiv  Detail & Related papers  (2025-10-27T17:43:51Z)
• Chess Rating Estimation from Moves and Clock Times Using a CNN-LSTM [11.340099493701029]
  We propose a method to estimate player ratings directly from game moves and clock times. Our model architecture comprises a CNN to learn positional features, which are integrated with clock-time data into a Bidirectional LSTM. This model is the first to use no hand-crafted features to estimate chess ratings and also the first to output a rating prediction after each move.
  arXiv  Detail & Related papers  (2024-09-17T19:19:16Z)
• Balance, Imbalance, and Rebalance: Understanding Robust Overfitting from a Minimax Game Perspective [80.51463286812314]
  Adversarial Training (AT) has become arguably the state-of-the-art algorithm for extracting robust features. AT suffers from severe robust overfitting problems, particularly after learning rate (LR) decay. We show how LR decay breaks the balance between the minimax game by empowering the trainer with a stronger memorization ability.
  arXiv  Detail & Related papers  (2023-10-30T09:00:11Z)
• EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens [57.354304637367555]
  We present EVEREST, a surprisingly efficient MVA approach for video representation learning. It finds tokens containing rich motion features and discards uninformative ones during both pre-training and fine-tuning. Our method significantly reduces the computation and memory requirements of MVA.
  arXiv  Detail & Related papers  (2022-11-19T09:57:01Z)
• Calibrated Learning to Defer with One-vs-All Classifiers [1.14219428942199]
  Learning to defer (L2D) framework has the potential to make AI systems safer. For a given input, the system can defer the decision to a human if the human is more likely than the model to take the correct action. We study the calibration of L2D systems, investigating if the probabilities they output are sound.
  arXiv  Detail & Related papers  (2022-02-08T06:24:06Z)
• Visibility Optimization for Surveillance-Evasion Games [4.454557728745761]
  We consider surveillance-evasion differential games, where a pursuer must try to constantly maintain visibility of a moving evader. We use an upwind scheme to compute the feedback value function, corresponding to the end-game time of the differential game. We show that Monte Carlo tree search and self-play reinforcement learning can train a deep neural network to generate reasonable strategies for on-line game play.
  arXiv  Detail & Related papers  (2020-10-18T15:02:41Z)
• Geometry-aware Instance-reweighted Adversarial Training [78.70024866515756]
  In adversarial machine learning, there was a common belief that robustness and accuracy hurt each other. We propose geometry-aware instance-reweighted adversarial training, where the weights are based on how difficult it is to attack a natural data point. Experiments show that our proposal boosts the robustness of standard adversarial training.
  arXiv  Detail & Related papers  (2020-10-05T01:33:11Z)
• Learning Zero-Sum Simultaneous-Move Markov Games Using Function Approximation and Correlated Equilibrium [116.56359444619441]
  We develop provably efficient reinforcement learning algorithms for two-player zero-sum finite-horizon Markov games. In the offline setting, we control both players and aim to find the Nash Equilibrium by minimizing the duality gap. In the online setting, we control a single player playing against an arbitrary opponent and aim to minimize the regret.
  arXiv  Detail & Related papers  (2020-02-17T17:04:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.