Learning to Plan via Supervised Contrastive Learning and Strategic Interpolation: A Chess Case Study

Modern chess engines achieve superhuman performance through deep tree search and regressive evaluation, while human players rely on intuition to select candidate moves followed by a shallow search to validate them. To model this intuition-driven planning process, we train a transformer encoder using supervised contrastive learning to embed board states into a latent space structured by positional evaluation. In this space, distance reflects evaluative similarity, and visualized trajectories display interpretable transitions between game states. We demonstrate that move selection can occur entirely within this embedding space by advancing toward favorable regions, without relying on deep search. Despite using only a 6-ply beam search, our model achieves an estimated Elo rating of 2593. Performance improves with both model size and embedding dimensionality, suggesting that latent planning may offer a viable alternative to traditional search. Although we focus on chess, the proposed embedding-based planning method can be generalized to other perfect-information games where state evaluations are learnable. All source code is available at https://github.com/andrewhamara/SOLIS.

Reasoning Can Hurt the Inductive Abilities of Large Language Models

Large Language Models (LLMs) have shown remarkable progress across domains, yet their ability to perform inductive reasoning - inferring latent rules from sparse examples - remains limited. It is often assumed that chain-of-thought (CoT) prompting, as used in Large Reasoning Models (LRMs), enhances such reasoning. We investigate this assumption with creating four controlled, diagnostic game-based tasks - chess, Texas Hold'em, dice games, and blackjack - with hidden human-defined rules. We find that CoT reasoning can degrade inductive performance, with LRMs often underperforming their non-reasoning counterparts. To explain this, we present a theoretical framework that reveals how reasoning steps can amplify error through three failure modes: incorrect sub-task decomposition, incorrect sub-task solving, and incorrect final answer summarization. Based on our theoretical and empirical analysis, we introduce structured interventions that adapt CoT generation according to our identified failure types. These interventions improve inductive accuracy without retraining. Our findings suggest that effective (CoT) reasoning depends not only on taking more steps but also on ensuring those steps are well-structured.

Vision Language Models are Biased

Large language models (LLMs) memorize a vast amount of prior knowledge from the Internet that help them on downstream tasks but also may notoriously sway their outputs towards wrong or biased answers. In this work, we test how the knowledge about popular subjects hurt the accuracy of vision language models (VLMs) on standard, objective visual tasks of counting and identification. We find that state-of-the-art VLMs are strongly biased (e.g, unable to recognize a fourth stripe has been added to a 3-stripe Adidas logo) scoring an average of 17.05% accuracy in counting (e.g., counting stripes in an Adidas-like logo) across 7 diverse domains from animals, logos, chess, board games, optical illusions, to patterned grids. Insert text (e.g., "Adidas") describing the subject name into the counterfactual image further decreases VLM accuracy. The biases in VLMs are so strong that instructing them to double-check their results or rely exclusively on image details to answer improves counting accuracy by only +2 points, on average. Our work presents an interesting failure mode in VLMs and an automated framework for testing VLM biases. Code and data are available at: vlmsarebiased.github.io.

Understanding the learned look-ahead behavior of chess neural networks

We investigate the look-ahead capabilities of chess-playing neural networks, specifically focusing on the Leela Chess Zero policy network. We build on the work of Jenner et al. (2024) by analyzing the model's ability to consider future moves and alternative sequences beyond the immediate next move. Our findings reveal that the network's look-ahead behavior is highly context-dependent, varying significantly based on the specific chess position. We demonstrate that the model can process information about board states up to seven moves ahead, utilizing similar internal mechanisms across different future time steps. Additionally, we provide evidence that the network considers multiple possible move sequences rather than focusing on a single line of play. These results offer new insights into the emergence of sophisticated look-ahead capabilities in neural networks trained on strategic tasks, contributing to our understanding of AI reasoning in complex domains. Our work also showcases the effectiveness of interpretability techniques in uncovering cognitive-like processes in artificial intelligence systems.

Soft Prompts for Evaluation: Measuring Conditional Distance of Capabilities

To help evaluate and understand the latent capabilities of language models, this paper introduces an approach using optimized input embeddings, or 'soft prompts,' as a metric of conditional distance between a model and a target behavior. The technique aims to facilitate latent capability discovery as a part of automated red teaming/evaluation suites and to provide quantitative feedback about the accessibility of potentially concerning behaviors in a way that may scale to powerful future models, including those which may otherwise be capable of deceptive alignment. An evaluation framework using soft prompts is demonstrated in natural language, chess, and pathfinding, and the technique is extended with generalized conditional soft prompts to aid in constructing task evaluations.

Enfoque Odychess: Un método dialéctico, constructivista y adaptativo para la enseñanza del ajedrez con inteligencias artificiales generativas

Chess teaching has evolved through different approaches, however, traditional methodologies, often based on memorization, contrast with the new possibilities offered by generative artificial intelligence, a technology still little explored in this field. This study seeks to empirically validate the effectiveness of the Odychess Approach in improving chess knowledge, strategic understanding, and metacognitive skills in students. A quasi-experimental study was conducted with a pre-test/post-test design and a control group (N=60). The experimental intervention implemented the Odychess Approach, incorporating a Llama 3.3 language model that was specifically adapted using Parameter-Efficient Fine-Tuning (PEFT) techniques to act as a Socratic chess tutor. Quantitative assessment instruments were used to measure chess knowledge, strategic understanding, and metacognitive skills before and after the intervention. The results of the quasi-experimental study showed significant improvements in the experimental group compared to the control group in the three variables analyzed: chess knowledge, strategic understanding, and metacognitive skills. The complementary qualitative analysis revealed greater analytical depth, more developed dialectical reasoning, and increased intrinsic motivation in students who participated in the Odychess method-based intervention. The Odychess Approach represents an effective pedagogical methodology for teaching chess, demonstrating the potential of the synergistic integration of constructivist and dialectical principles with generative artificial intelligence. The implications of this work are relevant for educators and institutions interested in adopting innovative pedagogical technologies and for researchers in the field of AI applied to education, highlighting the transferability of the language model adaptation methodology to other educational domains.

Policies of Multiple Skill Levels for Better Strength Estimation in Games

Accurately estimating human skill levels is crucial for designing effective human-AI interactions so that AI can provide appropriate challenges or guidance. In games where AI players have beaten top human professionals, strength estimation plays a key role in adapting AI behavior to match human skill levels. In a previous state-of-the-art study, researchers have proposed a strength estimator trained using human players' match data. Given some matches, the strength estimator computes strength scores and uses them to estimate player ranks (skill levels). In this paper, we focus on the observation that human players' behavior tendency varies according to their strength and aim to improve the accuracy of strength estimation by taking this into account. Specifically, in addition to strength scores, we obtain policies for different skill levels from neural networks trained using human players' match data. We then combine features based on these policies with the strength scores to estimate strength. We conducted experiments on Go and chess. For Go, our method achieved an accuracy of 80% in strength estimation when given 10 matches, which increased to 92% when given 20 matches. In comparison, the previous state-of-the-art method had an accuracy of 71% with 10 matches and 84% with 20 matches, demonstrating improvements of 8-9%. We observed similar improvements in chess. These results contribute to developing a more accurate strength estimation method and to improving human-AI interaction.

Leveraging Systems and Control Theory for Social Robotics: A Model-Based Behavioral Control Approach to Human-Robot Interaction

Social robots (SRs) should autonomously interact with humans, while exhibiting proper social behaviors associated to their role. By contributing to health-care, education, and companionship, SRs will enhance life quality. However, personalization and sustaining user engagement remain a challenge for SRs, due to their limited understanding of human mental states. Accordingly, we leverage a recently introduced mathematical dynamic model of human perception, cognition, and decision-making for SRs. Identifying the parameters of this model and deploying it in behavioral steering system of SRs allows to effectively personalize the responses of SRs to evolving mental states of their users, enhancing long-term engagement and personalization. Our approach uniquely enables autonomous adaptability of SRs by modeling the dynamics of invisible mental states, significantly contributing to the transparency and awareness of SRs. We validated our model-based control system in experiments with 10 participants who interacted with a Nao robot over three chess puzzle sessions, 45 - 90 minutes each. The identified model achieved a mean squared error (MSE) of 0.067 (i.e., 1.675% of the maximum possible MSE) in tracking beliefs, goals, and emotions of participants. Compared to a model-free controller that did not track mental states of participants, our approach increased engagement by 16% on average. Post-interaction feedback of participants (provided via dedicated questionnaires) further confirmed the perceived engagement and awareness of the model-driven robot. These results highlight the unique potential of model-based approaches and control theory in advancing human-SR interactions.

ZeroSumEval: Scaling LLM Evaluation with Inter-Model Competition

Evaluating the capabilities of Large Language Models (LLMs) has traditionally relied on static benchmark datasets, human assessments, or model-based evaluations - methods that often suffer from overfitting, high costs, and biases. ZeroSumEval is a novel competition-based evaluation protocol that leverages zero-sum games to assess LLMs with dynamic benchmarks that resist saturation. ZeroSumEval encompasses a diverse suite of games, including security challenges (PyJail), classic games (Chess, Liar's Dice, Poker), knowledge tests (MathQuiz), and persuasion challenges (Gandalf, Debate). These games are designed to evaluate a range of AI capabilities such as strategic reasoning, planning, knowledge application, and creativity. Building upon recent studies that highlight the effectiveness of game-based evaluations for LLMs, ZeroSumEval enhances these approaches by providing a standardized and extensible framework. To demonstrate this, we conduct extensive experiments with >7000 simulations across 7 games and 13 models. Our results show that while frontier models from the GPT and Claude families can play common games and answer questions, they struggle to play games that require creating novel and challenging questions. We also observe that models cannot reliably jailbreak each other and fail generally at tasks requiring creativity. We release our code at https://github.com/facebookresearch/ZeroSumEval.

pix2pockets: Shot Suggestions in 8-Ball Pool from a Single Image in the Wild

Computer vision models have seen increased usage in sports, and reinforcement learning (RL) is famous for beating humans in strategic games such as Chess and Go. In this paper, we are interested in building upon these advances and examining the game of classic 8-ball pool. We introduce pix2pockets, a foundation for an RL-assisted pool coach. Given a single image of a pool table, we first aim to detect the table and the balls and then propose the optimal shot suggestion. For the first task, we build a dataset with 195 diverse images where we manually annotate all balls and table dots, leading to 5748 object segmentation masks. For the second task, we build a standardized RL environment that allows easy development and benchmarking of any RL algorithm. Our object detection model yields an AP50 of 91.2 while our ball location pipeline obtains an error of only 0.4 cm. Furthermore, we compare standard RL algorithms to set a baseline for the shot suggestion task and we show that all of them fail to pocket all balls without making a foul move. We also present a simple baseline that achieves a per-shot success rate of 94.7% and clears a full game in a single turn 30% of the time.