# Beyond Asking: A Pipeline for Personalized Game Generation that Reads Players from Behavior

arXiv: https://arxiv.org/abs/2608.16196 · HTML: https://mlsanity.com/paper/2608.16196/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 49 references that are in the map.
- First posted on arXiv 17 Aug 2026.

## Builds on (most cited first, 12 of 12)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [Validating Bayesian Inference Algorithms with Simulation-Based Calibration](https://mlsanity.com/paper/1804.06788/) (2018)
- [Large Language Models and Games: A Survey and Roadmap](https://mlsanity.com/paper/2402.18659/) (2024)
- [Large Language Model Psychometrics: A Systematic Review of Evaluation, Validation, and Enhancement](https://mlsanity.com/paper/2505.08245/) (2025)
- [Automated Playtesting with Procedural Personas through MCTS with Evolved Heuristics](https://mlsanity.com/paper/1802.06881/) (2018)
- [Large Language Models Can Infer Personality from Free-Form User Interactions](https://mlsanity.com/paper/2405.13052/) (2024)
- [Modeling Individual Differences in Game Behavior using HMM](https://mlsanity.com/paper/1804.00245/) (2018)
- [Can LLMs Infer Personality from Real World Conversations?](https://mlsanity.com/paper/2507.14355/) (2025)
- [Evaluating LLM Alignment on Personality Inference from Real-World Interview Data](https://mlsanity.com/paper/2509.13244/) (2025)
- [Label-Free Subjective Player Experience Modelling via Let's Play Videos](https://mlsanity.com/paper/2410.02967/) (2024)
- [Can we infer player behavior tendencies from a player's decision-making data? Integrating Theory of Mind to Player Modeling](https://mlsanity.com/paper/2107.11963/) (2021)

## Built on by (most cited first, 1 of 1)

- [AI for Games in the Foundation Model Era](https://mlsanity.com/paper/2609.16679/) (2026)

## Abstract (arXiv)

Personalized game generation requires inferring a player's abilities and behavioral style from how they play. Large language models have made this inference more attainable than ever: an LLM can read a raw gameplay transcript and produce a fluent, plausible profile of the player. Plausible, however, is not verified, and verification is precisely what the field lacks: latent traits are unobservable; questionnaires provide noisy proxies and become circular when self-reports are used to validate behavior-based inference; and behavior itself is ambiguous without context -- a player who never collects an item may not want it, or may never have had the chance. We address both problems. First, we construct a synthetic player population whose traits are ground truth by construction: each trait is an explicit bot parameter, accepted only after controlled manipulation produces consistent, trait-specific behavioral change. Unlike prior parameter-recovery work that inverts a known decision model, our benchmark evaluates policy-agnostic inference from behavioral transcripts alone. Second, we introduce an opportunity-aware decision-moment representation that disentangles preference from the chance to express it; ablating it selectively degrades opportunity-dependent traits. On this benchmark, few-shot LLM inference outperforms embedding- and rule-based baselines on most traits, though feature-based supervised regressors remain stronger overall. Finally, we close the loop: inferred profiles drive difficulty adaptation, evaluated against ground-truth references and mismatched-profile controls, and an exploratory human study examines whether these findings transfer to real players.