{"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/chemical-reasoning-in-llms-unlocks-steerable","title":"Chemical reasoning in LLMs unlocks steerable synthesis planning and reaction mechanism elucidation","arxiv_id":"2503.08537","date":"2025-03-11","proceeding":null,"authors":["Andres M Bran","Theo A Neukomm","Daniel P Armstrong","Zlatko Jončev","Philippe Schwaller"],"abstract":"While machine learning algorithms have been shown to excel at specific chemical tasks, they have struggled to capture the strategic thinking that characterizes expert chemical reasoning, limiting their widespread adoption. Here we demonstrate that large language models (LLMs) can serve as powerful chemical reasoning engines when integrated with traditional search algorithms, enabling a new approach to computer-aided chemistry that mirrors human expert thinking. Rather than using LLMs to directly manipulate chemical structures, we leverage their ability to evaluate chemical strategies and guide search algorithms toward chemically meaningful solutions. We demonstrate this paradigm through two fundamental challenges: strategy-aware retrosynthetic planning and mechanism elucidation. In retrosynthetic planning, our method allows chemists to specify desired synthetic strategies in natural language to find routes that satisfy these constraints in vast searches. In mechanism elucidation, LLMs guide the search for plausible reaction mechanisms by combining chemical principles with systematic exploration. Our approach shows strong performance across diverse chemical tasks, with larger models demonstrating increasingly sophisticated chemical reasoning. Our approach establishes a new paradigm for computer-aided chemistry that combines the strategic understanding of LLMs with the precision of traditional chemical tools, opening possibilities for more intuitive and powerful chemical reasoning systems.","url_abs":"https://arxiv.org/abs/2503.08537v1","url_pdf":"https://arxiv.org/pdf/2503.08537v1.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":"chemical-reasoning-in-llms-unlocks-steerable","repo_url":"https://github.com/schwallergroup/steer","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2503.08537","atlas_url":"https://app.syntology.ai/?focus=2503.08537","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.08537"}},"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/schwallergroup/steer","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"ran_honours":1},"by_repo_kind":{"official":{"samples":4,"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":"1437a283b1c4763f","entry":"format_path","repo":"schwallergroup/steer","repo_kind":"official","path":"src/steer/mechanism/astar.py","file_url":"https://github.com/schwallergroup/steer/blob/HEAD/src/steer/mechanism/astar.py","link_basis":"harvester_set","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":"1437a283b1c4763f"}},{"code_sha256_prefix":"4f2bf2d5e80a790f","entry":"opposite_score","repo":"schwallergroup/steer","repo_kind":"official","path":"src/steer/mechanism/search_algo.py","file_url":"https://github.com/schwallergroup/steer/blob/HEAD/src/steer/mechanism/search_algo.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4f2bf2d5e80a790f"}},{"code_sha256_prefix":"1f00017309f3b210","entry":"setup_logger","repo":"schwallergroup/steer","repo_kind":"official","path":"src/steer/logger.py","file_url":"https://github.com/schwallergroup/steer/blob/HEAD/src/steer/logger.py","link_basis":"harvester_set","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":"1f00017309f3b210"}},{"code_sha256_prefix":"c0cf1196424d4f71","entry":"softmax","repo":"schwallergroup/steer","repo_kind":"official","path":"src/steer/mechanism/search.py","file_url":"https://github.com/schwallergroup/steer/blob/HEAD/src/steer/mechanism/search.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c0cf1196424d4f71"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}