{"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/language-modeling-by-language-models","title":"Language Modeling by Language Models","arxiv_id":"2506.20249","date":"2025-06-25","proceeding":null,"authors":["Junyan Cheng","Peter Clark","Kyle Richardson"],"abstract":"Can we leverage LLMs to model the process of discovering novel language model (LM) architectures? Inspired by real research, we propose a multi-agent LLM approach that simulates the conventional stages of research, from ideation and literature search (proposal stage) to design implementation (code generation), generative pre-training, and downstream evaluation (verification). Using ideas from scaling laws, our system, Genesys, employs a Ladder of Scales approach; new designs are proposed, adversarially reviewed, implemented, and selectively verified at increasingly larger model scales (14M$\\sim$350M parameters) with a narrowing budget (the number of models we can train at each scale). To help make discovery efficient and factorizable, Genesys uses a novel genetic programming backbone, which we show has empirical advantages over commonly used direct prompt generation workflows (e.g., $\\sim$86\\% percentage point improvement in successful design generation, a key bottleneck). We report experiments involving 1,162 newly discovered designs (1,062 fully verified through pre-training) and find the best designs to be highly competitive with known architectures (e.g., outperform GPT2, Mamba2, etc., on 6/9 common benchmarks). We couple these results with comprehensive system-level ablations and formal results, which give broader insights into the design of effective autonomous discovery systems.","url_abs":"https://arxiv.org/abs/2506.20249v1","url_pdf":"https://arxiv.org/pdf/2506.20249v1.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":"language-modeling-by-language-models","repo_url":"https://github.com/allenai/genesys","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}}],"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":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2506.20249","atlas_url":"https://app.syntology.ai/?focus=2506.20249","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.20249"}},"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/allenai/genesys","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"ran":0,"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":"d6ac30a94d56959f","entry":"dict_eq","repo":"allenai/genesys","repo_kind":"official","path":"model_discovery/utils.py","file_url":"https://github.com/allenai/genesys/blob/HEAD/model_discovery/utils.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":"d6ac30a94d56959f"}},{"code_sha256_prefix":"df3caafe9e280578","entry":"index_chunk_tool","repo":"allenai/genesys","repo_kind":"official","path":"model_discovery/evolution.py","file_url":"https://github.com/allenai/genesys/blob/HEAD/model_discovery/evolution.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":"df3caafe9e280578"}},{"code_sha256_prefix":"49f874e390fe5027","entry":"letternum2num","repo":"allenai/genesys","repo_kind":"official","path":"model_discovery/utils.py","file_url":"https://github.com/allenai/genesys/blob/HEAD/model_discovery/utils.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":"49f874e390fe5027"}},{"code_sha256_prefix":"e4b2e38a8bb978ef","entry":"read_index","repo":"allenai/genesys","repo_kind":"official","path":"model_discovery/evolution.py","file_url":"https://github.com/allenai/genesys/blob/HEAD/model_discovery/evolution.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":"e4b2e38a8bb978ef"}},{"code_sha256_prefix":"1c79f1640254bc44","entry":"strscale","repo":"allenai/genesys","repo_kind":"official","path":"model_discovery/utils.py","file_url":"https://github.com/allenai/genesys/blob/HEAD/model_discovery/utils.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":"1c79f1640254bc44"}},{"code_sha256_prefix":"8e03183878b9f4d8","entry":"theme_aware_options","repo":"allenai/genesys","repo_kind":"official","path":"bin/app_utils.py","file_url":"https://github.com/allenai/genesys/blob/HEAD/bin/app_utils.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":"8e03183878b9f4d8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}