{"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/chemreasoner-heuristic-search-over-a-large","title":"ChemReasoner: Heuristic Search over a Large Language Model's Knowledge Space using Quantum-Chemical Feedback","arxiv_id":"2402.10980","date":"2024-02-15","proceeding":null,"authors":["Henry W. Sprueill","Carl Edwards","Khushbu Agarwal","Mariefel V. Olarte","Udishnu Sanyal","Conrad Johnston","Hongbin Liu","Heng Ji","Sutanay Choudhury"],"abstract":"The discovery of new catalysts is essential for the design of new and more efficient chemical processes in order to transition to a sustainable future. We introduce an AI-guided computational screening framework unifying linguistic reasoning with quantum-chemistry based feedback from 3D atomistic representations. Our approach formulates catalyst discovery as an uncertain environment where an agent actively searches for highly effective catalysts via the iterative combination of large language model (LLM)-derived hypotheses and atomistic graph neural network (GNN)-derived feedback. Identified catalysts in intermediate search steps undergo structural evaluation based on spatial orientation, reaction pathways, and stability. Scoring functions based on adsorption energies and reaction energy barriers steer the exploration in the LLM's knowledge space toward energetically favorable, high-efficiency catalysts. We introduce planning methods that automatically guide the exploration without human input, providing competitive performance against expert-enumerated chemical descriptor-based implementations. By integrating language-guided reasoning with computational chemistry feedback, our work pioneers AI-accelerated, trustworthy catalyst discovery.","url_abs":"https://arxiv.org/abs/2402.10980v5","url_pdf":"https://arxiv.org/pdf/2402.10980v5.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":"chemreasoner-heuristic-search-over-a-large","repo_url":"https://github.com/pnnl/chemreasoner","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"computational-chemistry","task_name":"Computational chemistry"},{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"},{"task_slug":"heuristic-search","task_name":"Heuristic Search"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"}],"methods":[{"method_slug":"graph-neural-network","method_name":"Graph Neural Network"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.10980","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10980"}},"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/pnnl/chemreasoner","reach":null}],"summary":{"ran_draft_wrong":2,"ran":3,"unverified":2},"by_repo_kind":{"official":{"samples":7,"ran":5,"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":7,"samples":[{"code_sha256_prefix":"60724ebc4ce5a746","entry":"convert_to_string","repo":"pnnl/chemreasoner","repo_kind":"official","path":"src/search/state/reasoner_state.py","file_url":"https://github.com/pnnl/chemreasoner/blob/HEAD/src/search/state/reasoner_state.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"60724ebc4ce5a746"}},{"code_sha256_prefix":"e23f5c50c52a38d0","entry":"fstr","repo":"pnnl/chemreasoner","repo_kind":"official","path":"src/search/state/reasoner_state.py","file_url":"https://github.com/pnnl/chemreasoner/blob/HEAD/src/search/state/reasoner_state.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"e23f5c50c52a38d0"}},{"code_sha256_prefix":"9fa4ecc48250be00","entry":"generate_adsorption_energy_list_prompt","repo":"pnnl/chemreasoner","repo_kind":"official","path":"src/search/state/reasoner_state.py","file_url":"https://github.com/pnnl/chemreasoner/blob/HEAD/src/search/state/reasoner_state.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"9fa4ecc48250be00"}},{"code_sha256_prefix":"2babba9bf041fb33","entry":"load_sim_trees","repo":"pnnl/chemreasoner","repo_kind":"official","path":"src/evaluation/chemreasoner_coherence_evaluation.py","file_url":"https://github.com/pnnl/chemreasoner/blob/HEAD/src/evaluation/chemreasoner_coherence_evaluation.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"2babba9bf041fb33"}},{"code_sha256_prefix":"8ad4e051476a3e90","entry":"parse_answer","repo":"pnnl/chemreasoner","repo_kind":"official","path":"src/search/state/reasoner_state.py","file_url":"https://github.com/pnnl/chemreasoner/blob/HEAD/src/search/state/reasoner_state.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"8ad4e051476a3e90"}},{"code_sha256_prefix":"3725e3d4a3318ddd","entry":"ReasonerState","repo":"pnnl/chemreasoner","repo_kind":"official","path":"src/search/state/reasoner_state.py","file_url":"https://github.com/pnnl/chemreasoner/blob/HEAD/src/search/state/reasoner_state.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"3725e3d4a3318ddd"}},{"code_sha256_prefix":"ebc1c7ad9a578aff","entry":"generate_expert_prompt","repo":"pnnl/chemreasoner","repo_kind":"official","path":"src/search/state/reasoner_state.py","file_url":"https://github.com/pnnl/chemreasoner/blob/HEAD/src/search/state/reasoner_state.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"ebc1c7ad9a578aff"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}