{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/subgoal-search-for-complex-reasoning-tasks","title":"Subgoal Search For Complex Reasoning Tasks","arxiv_id":"2108.11204","date":"2021-08-25","proceeding":"NeurIPS 2021 12","authors":["Konrad Czechowski","Tomasz Odrzygóźdź","Marek Zbysiński","Michał Zawalski","Krzysztof Olejnik","Yuhuai Wu","Łukasz Kuciński","Piotr Miłoś"],"abstract":"Humans excel in solving complex reasoning tasks through a mental process of moving from one idea to a related one. Inspired by this, we propose Subgoal Search (kSubS) method. Its key component is a learned subgoal generator that produces a diversity of subgoals that are both achievable and closer to the solution. Using subgoals reduces the search space and induces a high-level search graph suitable for efficient planning. In this paper, we implement kSubS using a transformer-based subgoal module coupled with the classical best-first search framework. We show that a simple approach of generating $k$-th step ahead subgoals is surprisingly efficient on three challenging domains: two popular puzzle games, Sokoban and the Rubik's Cube, and an inequality proving benchmark INT. kSubS achieves strong results including state-of-the-art on INT within a modest computational budget.","url_abs":"https://arxiv.org/abs/2108.11204v3","url_pdf":"https://arxiv.org/pdf/2108.11204v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"subgoal-search-for-complex-reasoning-tasks","repo_url":"https://github.com/subgoal-search/subgoal-search","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"rubik-s-cube","task_name":"Rubik's Cube"},{"task_slug":"sokoban","task_name":"Sokoban"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2108.11204","atlas_url":"https://app.syntology.ai/?focus=2108.11204","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}