{"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/self-taught-optimizer-stop-recursively-self","title":"Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation","arxiv_id":"2310.02304","date":"2023-10-03","proceeding":null,"authors":["Eric Zelikman","Eliana Lorch","Lester Mackey","Adam Tauman Kalai"],"abstract":"Several recent advances in AI systems solve problems by providing a \"scaffolding\" program that structures multiple calls to language models (LMs) to generate better outputs. A scaffolding program is written in a programming language such as Python. In this work, we use a language-model-infused scaffolding program to improve itself. We start with a seed \"improver\" that improves an input program according to a given utility function by querying an LM several times and returning the best solution. We then run this seed improver to improve itself. Across a small set of downstream tasks, the resulting improved improver generates programs with significantly better performance than its seed improver. A variety of self-improvement strategies are proposed by the language model, including beam search, genetic algorithms, and simulated annealing. Since the language models themselves are not altered, this is not full recursive self-improvement. Nonetheless, it demonstrates that a modern language model, GPT-4 in our experiments, is capable of writing code that can call itself to improve itself. We consider concerns around the development of self-improving technologies and evaluate the frequency with which the generated code bypasses a sandbox.","url_abs":"https://arxiv.org/abs/2310.02304v3","url_pdf":"https://arxiv.org/pdf/2310.02304v3.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":"self-taught-optimizer-stop-recursively-self","repo_url":"https://github.com/microsoft/stop","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"code-generation","task_name":"Code Generation"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-4","method_name":"GPT-4"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2310.02304","atlas_url":"https://app.syntology.ai/?focus=2310.02304","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.02304"}},"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/microsoft/stop","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4,"unverified":3},"by_repo_kind":{"official":{"samples":7,"ran":4,"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":"948a2eb852c7d75e","entry":"algorithm","repo":"microsoft/stop","repo_kind":"official","path":"tasks/maxcut/seed_algorithm.py","file_url":"https://github.com/microsoft/stop/blob/HEAD/tasks/maxcut/seed_algorithm.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"948a2eb852c7d75e"}},{"code_sha256_prefix":"7e0ada009b7cf021","entry":"algorithm","repo":"microsoft/stop","repo_kind":"official","path":"tasks/modified_quadratic_assignment/seed_algorithm.py","file_url":"https://github.com/microsoft/stop/blob/HEAD/tasks/modified_quadratic_assignment/seed_algorithm.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7e0ada009b7cf021"}},{"code_sha256_prefix":"4ba2a1030ad49f51","entry":"algorithm","repo":"microsoft/stop","repo_kind":"official","path":"tasks/three_sat/seed_algorithm.py","file_url":"https://github.com/microsoft/stop/blob/HEAD/tasks/three_sat/seed_algorithm.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4ba2a1030ad49f51"}},{"code_sha256_prefix":"bdcd923bdde3921f","entry":"random_walk_solver","repo":"microsoft/stop","repo_kind":"official","path":"tasks/three_sat/seed_algorithm.py","file_url":"https://github.com/microsoft/stop/blob/HEAD/tasks/three_sat/seed_algorithm.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bdcd923bdde3921f"}},{"code_sha256_prefix":"dc62532cec8323f5","entry":"extract_code","repo":"microsoft/stop","repo_kind":"official","path":"helpers.py","file_url":"https://github.com/microsoft/stop/blob/HEAD/helpers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dc62532cec8323f5"}},{"code_sha256_prefix":"d7a13e94854d7e2c","entry":"find_largest_code_block_line_by_line","repo":"microsoft/stop","repo_kind":"official","path":"helpers.py","file_url":"https://github.com/microsoft/stop/blob/HEAD/helpers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d7a13e94854d7e2c"}},{"code_sha256_prefix":"d9043050b18efcd6","entry":"run_by_creating_file","repo":"microsoft/stop","repo_kind":"official","path":"helpers.py","file_url":"https://github.com/microsoft/stop/blob/HEAD/helpers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d9043050b18efcd6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}