paper-with-me

홈 › Papers

Evaluating Language Models' Evaluations of Games

2025-10-13 · Katherine M. Collins, Cedegao E. Zhang, Graham Todd, Lance Ying, Mauricio Barba da Costa, Ryan Liu, Prafull Sharma, Adrian Weller, Ionatan Kuperwajs, Lionel Wong, Joshua B. Tenenbaum, Thomas L. Griffiths arxiv

Reasoning is not just about solving problems -- it is also about evaluating which problems are worth solving at all. Evaluations of artificial intelligence (AI) systems primarily focused on problem solving, historically by studying how models play games such as chess and Go. In this paper, we advocate for a new paradigm that assesses AI systems' evaluation of games. First, we introduce a formalism for evaluating such evaluations. We then leverage a large-scale dataset of over 100 novel board games and over 450 human judgments to compare evaluations produced by modern language and reasoning models against those of people and symbolic computational agents. We consider two kinds of evaluative queries: assessing the payoff (or fairness) and the funness of games. These queries span two dimensions relevant to the design of evaluations of AI evaluations: how complex a query is to compute and how difficult a query is to quantify. Our results show that reasoning models are generally more aligned to people in their evaluations of games than non-reasoning language models. However, we observe a non-monotonic relationship: as models get closer to game-theoretic optimal, their fit to human data weakens. We also observe more "jaggedness" across models for assessing funness, in line with the greater difficulty of quantifying this query. Across queries and games, reasoning models show highly variable and unpredictable resource usage when assessing queries, pointing to the importance of imbuing more resource-rational meta-reasoning in language and reasoning models.

📄 PDF Abstract BibTeX arXiv:2510.10930

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

GameBench: Evaluating Strategic Reasoning Abilities of LLM Agents

2024-06-07 · Anthony Costarelli, Mat Allen, Roman Hauksson, Grace Sodunke 외

Large language models have demonstrated remarkable few-shot performance on many natural language understanding tasks. Despite several demonstrations of using large language models in complex, strategic scenarios, there l…

Natural Language Understanding

ZeroSumEval: Scaling LLM Evaluation with Inter-Model Competition

2025-04-17 · Haidar Khan, Hisham A. Alyahya, Yazeed Alnumay, M Saiful Bari 외

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, a…

model

Games for AI Control: Models of Safety Evaluations of AI Deployment Protocols

2024-09-12 · Charlie Griffin, Louis Thomson, Buck Shlegeris, Alessandro Abate

To evaluate the safety and usefulness of deployment protocols for untrusted AIs, AI Control uses a red-teaming exercise played between a protocol designer and an adversary. This paper introduces AI-Control Games, a forma…

Decision MakingRed Teaming

GVGAI-LLM: Evaluating Large Language Model Agents with Infinite Games

2025-08-11 · Yuchen Li, Cong Lin, Muhammad Umair Nasir, Philip Bontrager 외 arxiv

We introduce GVGAI-LLM, a video game benchmark for evaluating the reasoning and problem-solving capabilities of large language models (LLMs). Built on the General Video Game AI framework, it features a diverse collection…

Spatial Reasoning

Shared Task on Evaluating Accuracy

2020-12-01 · INLG (ACL) 2020 12 · Ehud Reiter, Craig Thomson

We propose a shared task on methodologies and algorithms for evaluating the accuracy of generated texts, specifically summaries of basketball games produced from basketball box score and other game data. We welcome submi…