{"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/chemcrow-augmenting-large-language-models","title":"ChemCrow: Augmenting large-language models with chemistry tools","arxiv_id":"2304.05376","date":"2023-04-11","proceeding":null,"authors":["Andres M Bran","Sam Cox","Oliver Schilter","Carlo Baldassari","Andrew D White","Philippe Schwaller"],"abstract":"Over the last decades, excellent computational chemistry tools have been developed. Integrating them into a single platform with enhanced accessibility could help reaching their full potential by overcoming steep learning curves. Recently, large-language models (LLMs) have shown strong performance in tasks across domains, but struggle with chemistry-related problems. Moreover, these models lack access to external knowledge sources, limiting their usefulness in scientific applications. In this study, we introduce ChemCrow, an LLM chemistry agent designed to accomplish tasks across organic synthesis, drug discovery, and materials design. By integrating 18 expert-designed tools, ChemCrow augments the LLM performance in chemistry, and new capabilities emerge. Our agent autonomously planned and executed the syntheses of an insect repellent, three organocatalysts, and guided the discovery of a novel chromophore. Our evaluation, including both LLM and expert assessments, demonstrates ChemCrow's effectiveness in automating a diverse set of chemical tasks. Surprisingly, we find that GPT-4 as an evaluator cannot distinguish between clearly wrong GPT-4 completions and Chemcrow's performance. Our work not only aids expert chemists and lowers barriers for non-experts, but also fosters scientific advancement by bridging the gap between experimental and computational chemistry.","url_abs":"https://arxiv.org/abs/2304.05376v5","url_pdf":"https://arxiv.org/pdf/2304.05376v5.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":"chemcrow-augmenting-large-language-models","repo_url":"https://github.com/ur-whitelab/chemcrow-public","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"chemcrow-augmenting-large-language-models","repo_url":"https://github.com/ur-whitelab/chemcrow-runs","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"chemcrow-augmenting-large-language-models","repo_url":"https://github.com/whitead/synspace","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"computational-chemistry","task_name":"Computational chemistry"},{"task_slug":"drug-discovery","task_name":"Drug Discovery"}],"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":"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":{"atlas_url":"https://app.syntology.ai/?focus=2304.05376","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.05376"}},"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/whitead/synspace","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ur-whitelab/chemcrow-runs","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ur-whitelab/chemcrow-public","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_violates":1,"unverified":2},"by_repo_kind":{"official":{"samples":3,"ran":1,"repositories":2}},"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":"e63e29d520bb580b","entry":"prob_transform","repo":"whitead/synspace","repo_kind":"official","path":"synspace/synspace.py","file_url":"https://github.com/whitead/synspace/blob/HEAD/synspace/synspace.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e63e29d520bb580b"}},{"code_sha256_prefix":"661e00d0d5e73e4f","entry":"cdk","repo":"ur-whitelab/chemcrow-public","repo_kind":"official","path":"chemcrow/frontend/utils.py","file_url":"https://github.com/ur-whitelab/chemcrow-public/blob/HEAD/chemcrow/frontend/utils.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":"661e00d0d5e73e4f"}},{"code_sha256_prefix":"f783d2df77535339","entry":"split_smiles","repo":"ur-whitelab/chemcrow-public","repo_kind":"official","path":"chemcrow/utils.py","file_url":"https://github.com/ur-whitelab/chemcrow-public/blob/HEAD/chemcrow/utils.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":"f783d2df77535339"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}