Solving rubiks cubes "without search"

Alicja Ziarko and co-authors posted arXiv paper 2508.13113v2 on 29 September 2025 introducing Combinatorial Representations for Temporal Reasoning (CRTR), a method that uses a negative sampling scheme to remove spurious features from temporal contrastive learning. CRTR learns representations that generalize across all initial states of a Rubik's Cube and solve the puzzle using fewer search steps than BestFS, though with longer solutions, which the authors call the first method to efficiently solve arbitrary Cube states using only learned representations without an external search algorithm. The method also achieves strong results on Sokoban.

Computer Science Machine Learning Submitted on 18 Aug 2025 v1 https://arxiv.org/abs/2508.13113v1 , last revised 29 Sep 2025 this version, v2 Title:Contrastive Representations for Temporal Reasoning View PDF https://arxiv.org/pdf/2508.13113 HTML experimental https://arxiv.org/html/2508.13113v2 Abstract:In classical AI, perception relies on learning state-based representations, while planning, which can be thought of as temporal reasoning over action sequences, is typically achieved through search. We study whether such reasoning can instead emerge from representations that capture both perceptual and temporal structure. We show that standard temporal contrastive learning, despite its popularity, often fails to capture temporal structure due to its reliance on spurious features. To address this, we introduce Combinatorial Representations for Temporal Reasoning CRTR , a method that uses a negative sampling scheme to provably remove these spurious features and facilitate temporal reasoning. CRTR achieves strong results on domains with complex temporal structure, such as Sokoban and Rubik's Cube. In particular, for the Rubik's Cube, CRTR learns representations that generalize across all initial states and allow it to solve the puzzle using fewer search steps than BestFS, though with longer solutions. To our knowledge, this is the first method that efficiently solves arbitrary Cube states using only learned representations, without relying on an external search algorithm. Submission history From: Alicja Ziarko view email https://arxiv.org/show-email/b2a487d2/2508.13113 Mon, 18 Aug 2025 17:20:08 UTC 7,729 KB \ v1\ https://arxiv.org/abs/2508.13113v1 v2 Mon, 29 Sep 2025 14:34:40 UTC 7,736 KB References & Citations Loading... Bibliographic and Citation Tools Bibliographic Explorer What is the Explorer? https://info.arxiv.org/labs/showcase.html arxiv-bibliographic-explorer Connected Papers What is Connected Papers? https://www.connectedpapers.com/about Litmaps What is Litmaps? https://www.litmaps.co/ scite Smart Citations What are Smart Citations? https://www.scite.ai/ Code, Data and Media Associated with this Article alphaXiv What is alphaXiv? https://alphaxiv.org/ CatalyzeX Code Finder for Papers What is CatalyzeX? https://www.catalyzex.com DagsHub What is DagsHub? https://dagshub.com/ Gotit.pub What is GotitPub? http://gotit.pub/faq Hugging Face What is Huggingface? https://huggingface.co/huggingface ScienceCast What is ScienceCast? https://sciencecast.org/welcome Demos Recommenders and Search Tools Influence Flower What are Influence Flowers? https://influencemap.cmlab.dev/ CORE Recommender What is CORE? https://core.ac.uk/services/recommender IArxiv Recommender What is IArxiv? https://iarxiv.org/about arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs https://info.arxiv.org/labs/index.html .