{"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/crossbeam-learning-to-search-in-bottom-up-1","title":"CrossBeam: Learning to Search in Bottom-Up Program Synthesis","arxiv_id":"2203.10452","date":"2022-03-20","proceeding":"ICLR 2022 4","authors":["Kensen Shi","Hanjun Dai","Kevin Ellis","Charles Sutton"],"abstract":"Many approaches to program synthesis perform a search within an enormous space of programs to find one that satisfies a given specification. Prior works have used neural models to guide combinatorial search algorithms, but such approaches still explore a huge portion of the search space and quickly become intractable as the size of the desired program increases. To tame the search space blowup, we propose training a neural model to learn a hands-on search policy for bottom-up synthesis, instead of relying on a combinatorial search algorithm. Our approach, called CrossBeam, uses the neural model to choose how to combine previously-explored programs into new programs, taking into account the search history and partial program executions. Motivated by work in structured prediction on learning to search, CrossBeam is trained on-policy using data extracted from its own bottom-up searches on training tasks. We evaluate CrossBeam in two very different domains, string manipulation and logic programming. We observe that CrossBeam learns to search efficiently, exploring much smaller portions of the program space compared to the state-of-the-art.","url_abs":"https://arxiv.org/abs/2203.10452v1","url_pdf":"https://arxiv.org/pdf/2203.10452v1.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":"crossbeam-learning-to-search-in-bottom-up-1","repo_url":"https://github.com/google-research/crossbeam","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"program-synthesis","task_name":"Program Synthesis"},{"task_slug":"structured-prediction","task_name":"Structured Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2203.10452","atlas_url":"https://app.syntology.ai/?focus=2203.10452","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.10452"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/google-research/crossbeam","reach":null}],"summary":{"ran_draft_wrong":1,"unverified":5},"by_repo_kind":{"official":{"samples":6,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"d66de1c630616a06","entry":"beam_search","repo":"google-research/crossbeam","repo_kind":"official","path":"crossbeam/algorithm/synthesis.py","file_url":"https://github.com/google-research/crossbeam/blob/HEAD/crossbeam/algorithm/synthesis.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d66de1c630616a06"}},{"code_sha256_prefix":"0685fc573dd40aa9","entry":"copy_operation_value","repo":"google-research/crossbeam","repo_kind":"official","path":"crossbeam/algorithm/synthesis.py","file_url":"https://github.com/google-research/crossbeam/blob/HEAD/crossbeam/algorithm/synthesis.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0685fc573dd40aa9"}},{"code_sha256_prefix":"3e120a0b9c46f67a","entry":"init_values","repo":"google-research/crossbeam","repo_kind":"official","path":"crossbeam/algorithm/synthesis.py","file_url":"https://github.com/google-research/crossbeam/blob/HEAD/crossbeam/algorithm/synthesis.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3e120a0b9c46f67a"}},{"code_sha256_prefix":"675acb9ef15bac5e","entry":"synthesize","repo":"google-research/crossbeam","repo_kind":"official","path":"crossbeam/algorithm/synthesis.py","file_url":"https://github.com/google-research/crossbeam/blob/HEAD/crossbeam/algorithm/synthesis.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"675acb9ef15bac5e"}},{"code_sha256_prefix":"095b16af6c6e949c","entry":"update_masks","repo":"google-research/crossbeam","repo_kind":"official","path":"crossbeam/algorithm/synthesis.py","file_url":"https://github.com/google-research/crossbeam/blob/HEAD/crossbeam/algorithm/synthesis.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"095b16af6c6e949c"}},{"code_sha256_prefix":"64745a0a11dc8a44","entry":"update_with_better_value","repo":"google-research/crossbeam","repo_kind":"official","path":"crossbeam/algorithm/synthesis.py","file_url":"https://github.com/google-research/crossbeam/blob/HEAD/crossbeam/algorithm/synthesis.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"64745a0a11dc8a44"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}