{"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/improver-agent-based-automated-proof","title":"ImProver: Agent-Based Automated Proof Optimization","arxiv_id":"2410.04753","date":"2024-10-07","proceeding":null,"authors":["Riyaz Ahuja","Jeremy Avigad","Prasad Tetali","Sean Welleck"],"abstract":"Large language models (LLMs) have been used to generate formal proofs of mathematical theorems in proofs assistants such as Lean. However, we often want to optimize a formal proof with respect to various criteria, depending on its downstream use. For example, we may want a proof to adhere to a certain style, or to be readable, concise, or modularly structured. Having suitably optimized proofs is also important for learning tasks, especially since human-written proofs may not optimal for that purpose. To this end, we study a new problem of automated proof optimization: rewriting a proof so that it is correct and optimizes for an arbitrary criterion, such as length or readability. As a first method for automated proof optimization, we present ImProver, a large-language-model agent that rewrites proofs to optimize arbitrary user-defined metrics in Lean. We find that naively applying LLMs to proof optimization falls short, and we incorporate various improvements into ImProver, such as the use of symbolic Lean context in a novel Chain-of-States technique, as well as error-correction and retrieval. We test ImProver on rewriting real-world undergraduate, competition, and research-level mathematics theorems, finding that ImProver is capable of rewriting proofs so that they are substantially shorter, more modular, and more readable.","url_abs":"https://arxiv.org/abs/2410.04753v1","url_pdf":"https://arxiv.org/pdf/2410.04753v1.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":"improver-agent-based-automated-proof","repo_url":"https://github.com/riyazahuja/ImProver","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"improver-agent-based-automated-proof","repo_url":"https://github.com/cmu-l3/ntp-toolkit","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.04753","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.04753"}},"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/riyazahuja/ImProver","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cmu-l3/ntp-toolkit","reach":{"status":"ok"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"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":4,"samples":[{"code_sha256_prefix":"7adc3bfbf60b8306","entry":"extract_data","repo":"riyazahuja/ImProver","repo_kind":"official","path":"benchmark/tools.py","file_url":"https://github.com/riyazahuja/ImProver/blob/HEAD/benchmark/tools.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7adc3bfbf60b8306"}},{"code_sha256_prefix":"a4b46a2b3f066825","entry":"parse_prev_data","repo":"riyazahuja/ImProver","repo_kind":"official","path":"models/prompt.py","file_url":"https://github.com/riyazahuja/ImProver/blob/HEAD/models/prompt.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a4b46a2b3f066825"}},{"code_sha256_prefix":"a16a3745e6715f25","entry":"parse_trajectories","repo":"riyazahuja/ImProver","repo_kind":"official","path":"benchmark/tools.py","file_url":"https://github.com/riyazahuja/ImProver/blob/HEAD/benchmark/tools.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a16a3745e6715f25"}},{"code_sha256_prefix":"c527fcdb58d3d3fc","entry":"refinement","repo":"riyazahuja/ImProver","repo_kind":"official","path":"models/prompt.py","file_url":"https://github.com/riyazahuja/ImProver/blob/HEAD/models/prompt.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c527fcdb58d3d3fc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}