Newton to Einstein: Axiom-Based Discovery via Game Design

• URL: http://arxiv.org/abs/2509.05448v1
• Date: Fri, 05 Sep 2025 18:59:18 GMT
• Title: Newton to Einstein: Axiom-Based Discovery via Game Design
• Authors: Pingchuan Ma, Benjamin Tod Jones, Tsun-Hsuan Wang, Minghao Guo, Michal Piotr Lipiec, Chuang Gan, Wojciech Matusik,
• Abstract summary: We propose a game design framework in which scientific inquiry is recast as a rule-evolving system.<n>Unlike conventional ML approaches that operate within fixed assumptions, our method enables the discovery of new theoretical structures.
• Score: 55.30047000068118
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This position paper argues that machine learning for scientific discovery should shift from inductive pattern recognition to axiom-based reasoning. We propose a game design framework in which scientific inquiry is recast as a rule-evolving system: agents operate within environments governed by axioms and modify them to explain outlier observations. Unlike conventional ML approaches that operate within fixed assumptions, our method enables the discovery of new theoretical structures through systematic rule adaptation. We demonstrate the feasibility of this approach through preliminary experiments in logic-based games, showing that agents can evolve axioms that solve previously unsolvable problems. This framework offers a foundation for building machine learning systems capable of creative, interpretable, and theory-driven discovery.

Related papers

• NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agents [65.85967483058705]
  Large language models are emerging as powerful tools for scientific law discovery.<n>Existing benchmarks for this task suffer from a fundamental methodological trilemma.<n>We introduce NewtonBench, a benchmark comprising 324 scientific law discovery tasks across 12 physics domains.
  arXiv  Detail & Related papers  (2025-10-08T16:12:11Z)
• Active Inference AI Systems for Scientific Discovery [1.450405446885067]
  This perspective contends that progress turns on closing three mutually reinforcing gaps in abstraction, reasoning and empirical grounding.<n>Design principles are proposed for systems that reason in imaginary spaces and learn from the world.
  arXiv  Detail & Related papers  (2025-06-26T14:43:04Z)
• Reconceptualizing Smart Microscopy: From Data Collection to Knowledge Creation by Multi-Agent Integration [0.0]
  We introduce a theoretical framework that reconceptualizes smart microscopy as a partner in scientific investigation.<n>Our framework provides a roadmap for building microscopy systems that go beyond automation to actively support hypothesis generation, insight discovery, and theory development.
  arXiv  Detail & Related papers  (2025-05-26T19:02:14Z)
• The Buffer Mechanism for Multi-Step Information Reasoning in Language Models [52.77133661679439]
  Investigating internal reasoning mechanisms of large language models can help us design better model architectures and training strategies. In this study, we constructed a symbolic dataset to investigate the mechanisms by which Transformer models employ vertical thinking strategy. We proposed a random matrix-based algorithm to enhance the model's reasoning ability, resulting in a 75% reduction in the training time required for the GPT-2 model.
  arXiv  Detail & Related papers  (2024-05-24T07:41:26Z)
• LLM and Simulation as Bilevel Optimizers: A New Paradigm to Advance Physical Scientific Discovery [141.39722070734737]
  We propose to enhance the knowledge-driven, abstract reasoning abilities of Large Language Models with the computational strength of simulations. We introduce Scientific Generative Agent (SGA), a bilevel optimization framework. We conduct experiments to demonstrate our framework's efficacy in law discovery and molecular design.
  arXiv  Detail & Related papers  (2024-05-16T03:04:10Z)
• Mesarovician Abstract Learning Systems [0.0]
  Current approaches to learning hold notions of problem domain and problem task as fundamental precepts. Mesarovician abstract systems theory is used as a super-structure for learning.
  arXiv  Detail & Related papers  (2021-11-29T18:17:32Z)
• Observing Interventions: A logic for thinking about experiments [62.997667081978825]
  This paper makes a first step towards a logic of learning from experiments. Crucial for our approach is the idea that the notion of an intervention can be used as a formal expression of a (real or hypothetical) experiment. For all the proposed logical systems, we provide a sound and complete axiomatization.
  arXiv  Detail & Related papers  (2021-11-25T09:26:45Z)
• Formalising Concepts as Grounded Abstractions [68.24080871981869]
  This report shows how representation learning can be used to induce concepts from raw data. The main technical goal of this report is to show how techniques from representation learning can be married with a lattice-theoretic formulation of conceptual spaces.
  arXiv  Detail & Related papers  (2021-01-13T15:22:01Z)
• Physics guided machine learning using simplified theories [0.0]
  Recent applications of machine learning, in particular deep learning, motivate the need to address the generalizability of the statistical inference approaches in physical sciences. We introduce a modular physics guided machine learning framework to improve the accuracy of such data-driven predictive engines.
  arXiv  Detail & Related papers  (2020-12-18T21:30:40Z)
• Formalizing Falsification for Theories of Consciousness Across Computational Hierarchies [0.0]
  Integrated Information Theory (IIT) is widely regarded as the preeminent theory of consciousness. Epistemological issues in the form of the "unfolding argument" have provided a refutation of IIT. We show how IIT is simultaneously falsified at the finite-state automaton level and unfalsifiable at the state automaton level.
  arXiv  Detail & Related papers  (2020-06-12T18:05:46Z)
• A general framework for scientifically inspired explanations in AI [76.48625630211943]
  We instantiate the concept of structure of scientific explanation as the theoretical underpinning for a general framework in which explanations for AI systems can be implemented. This framework aims to provide the tools to build a "mental-model" of any AI system so that the interaction with the user can provide information on demand and be closer to the nature of human-made explanations.
  arXiv  Detail & Related papers  (2020-03-02T10:32:21Z)

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.