arXiv AI September 1, 2026 By Dien Nguyen, Diego Perez-Liebana

Game-Agnostic Value Functions through Automatic JSON Feature Extraction

The paper introduces JSON-Bag VF, a game-agnostic method for training value functions using JSON-Bag prototypes derived from tokenized game trajectories. It demonstrates that Random Forest-based feature selection and game-stage-specific feature selection enhance performance, and that these selections are more critical than prototype-tokenization. Experiments on six tabletop games show that JSON-Bag OSLA outperforms baseline one-step-look-ahead agents in most cases.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Computer Vision

Sep 22

GameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay

arXiv:2609.25001v1 Announce Type: new Abstract: Modern video games provide a measurable testbed for AI models, combining abilities of visual understanding, instruction decomposition, goal planning, a...

By Yiran Wang, Xingyilang Yin, Junfu Pu, Guangzhi Wang, Kaifeng Li, Mingyu Ouyang, Huiqiang Sun, Lingen Li, Cheng Cheng, Wangbo Yu, Honghao Chen, Xiaodong Cun, Chi-Man Pun, Zhiguo Cao, Ying Shan

benchmarks

arXiv AI

Jul 14

Comparative Analysis of GAT and BERT for Human-Like Playtesting

arXiv:2607. 11501v1 Announce Type: new Abstract: Accurately modeling and understanding player experience is crucial for designing engaging puzzle games.

By Kleio Fragkedaki, Theodoros Panagiotakopoulos, Matteo Biasielli, Hui Wang

llms

Hugging Face Trending Papers

Jul 13

Comparative Analysis of GAT and BERT for Human-Like Playtesting

Accurately modeling and understanding player experience is crucial for designing engaging puzzle games. To achieve this, a common approach involves collecting diverse user data to train predictive playtesting models that mimic player behavior.

llms

arXiv AI

Sep 7

Abstraction Agent

The paper introduces the Abstraction Agent, a zero‑shot pipeline that employs a large language model to automatically generate continuous strategic features from a natural‑language game description, score private states, and cluster them into abstraction buckets without any game‑specific evaluators or training data. The pipeline consists of four phases—feature discovery with calibration anchors, batched private‑state scoring, correlation‑based feature selection, and k‑means clustering—and achieves significant reductions in lifted‑strategy exploitability in heads‑up no‑limit Texas hold’em and outperforms scalar rank baselines in ROVER Trials. The method also transfers to other games such as four‑card Pot‑Limit Omaha, HUNL preflop and flop, and Riichi Mahjong, demonstrating that it can uncover strategic concepts that align with recognized game theory insights.

By Boning Li, Longbo Huang

llms agents benchmarks

arXiv Machine Learning

Jul 13

Application of machine learning to monster level prediction in tabletop RPG game design

arXiv:2607. 09196v1 Announce Type: new Abstract: Designing balanced adversaries is a central but labor-intensive task in tabletop role-playing game (TTRPG) development.

By Jolanta \'Sliwa, Jakub Adamczyk

arXiv AI

Jun 15

AFFORDANCE20Q: Evaluating Affordance Reasoning from Physical Properties

arXiv:2606. 14240v1 Announce Type: new Abstract: Affordance reasoning, the inference of an object's action possibilities from its physical properties (e.

By Yifan Jiang, Meige Yang, Zitong Li, Jay Pujara

llms benchmarks

One email a morning, machine-written

Related stories

GameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay

Comparative Analysis of GAT and BERT for Human-Like Playtesting

Comparative Analysis of GAT and BERT for Human-Like Playtesting

Abstraction Agent

Application of machine learning to monster level prediction in tabletop RPG game design

AFFORDANCE20Q: Evaluating Affordance Reasoning from Physical Properties