{"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/adaptive-self-improvement-llm-agentic-system","title":"Adaptive Self-improvement LLM Agentic System for ML Library Development","arxiv_id":"2502.02534","date":"2025-02-04","proceeding":null,"authors":["Genghan Zhang","Weixin Liang","Olivia Hsu","Kunle Olukotun"],"abstract":"ML libraries, often written in architecture-specific programming languages (ASPLs) that target domain-specific architectures, are key to efficient ML systems. However, writing these high-performance ML libraries is challenging because it requires expert knowledge of ML algorithms and the ASPL. Large language models (LLMs), on the other hand, have shown general coding capabilities. However, challenges remain when using LLMs for generating ML libraries using ASPLs because 1) this task is complicated even for experienced human programmers and 2) there are limited code examples because of the esoteric and evolving nature of ASPLs. Therefore, LLMs need complex reasoning with limited data in order to complete this task. To address these challenges, we introduce an adaptive self-improvement agentic system. In order to evaluate the effectiveness of our system, we construct a benchmark of a typical ML library and generate ASPL code with both open and closed-source LLMs on this benchmark. Our results show improvements of up to $3.9\\times$ over a baseline single LLM.","url_abs":"https://arxiv.org/abs/2502.02534v1","url_pdf":"https://arxiv.org/pdf/2502.02534v1.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":"adaptive-self-improvement-llm-agentic-system","repo_url":"https://github.com/zhang677/pcl-lite","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":null,"method_name":"Library"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2502.02534","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.02534"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/zhang677/pcl-lite","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"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":"d877decdbfa08296","entry":"check_ref_code","repo":"zhang677/pcl-lite","repo_kind":"official","path":"reinforce/actions.py","file_url":"https://github.com/zhang677/pcl-lite/blob/HEAD/reinforce/actions.py","link_basis":"harvester_set","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":"d877decdbfa08296"}},{"code_sha256_prefix":"8f0c95b68e092f0a","entry":"get_full_indices","repo":"zhang677/pcl-lite","repo_kind":"official","path":"step/ops.py","file_url":"https://github.com/zhang677/pcl-lite/blob/HEAD/step/ops.py","link_basis":"harvester_set","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":"8f0c95b68e092f0a"}},{"code_sha256_prefix":"2a4ad762e2eaa4d4","entry":"subsFlattenFullShape","repo":"zhang677/pcl-lite","repo_kind":"official","path":"step/base.py","file_url":"https://github.com/zhang677/pcl-lite/blob/HEAD/step/base.py","link_basis":"harvester_set","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":"2a4ad762e2eaa4d4"}},{"code_sha256_prefix":"f0788d007bdffb1f","entry":"subsFullShape","repo":"zhang677/pcl-lite","repo_kind":"official","path":"step/base.py","file_url":"https://github.com/zhang677/pcl-lite/blob/HEAD/step/base.py","link_basis":"harvester_set","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":"f0788d007bdffb1f"}},{"code_sha256_prefix":"b1fad8a2bfa7e6fb","entry":"subsOuterShape","repo":"zhang677/pcl-lite","repo_kind":"official","path":"step/base.py","file_url":"https://github.com/zhang677/pcl-lite/blob/HEAD/step/base.py","link_basis":"harvester_set","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":"b1fad8a2bfa7e6fb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}