{"paper":{"title":"Rongzai agent: A Large Language Model-Based Autonomous Assistant for Rietveld Refinement of Neutron Diffraction Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"An LLM-based agent autonomously refines neutron diffraction data and matches or beats human experts on fit quality.","cross_cats":[],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Bolun Zhang, Dongbo Xiong, Fazhi Qi, Hao Hu, Hao Wang, Hong Wang, Jiajun Zhong, JunRong Zhang, Qingmeng Li, Rong Du, Wenhai Ji, Yiyu Zhang, Yongfeng Zhu, Zhengde Zhang","submitted_at":"2026-05-13T08:16:31Z","abstract_excerpt":"Neutron diffraction (ND) is an indispensable technique for determining atomic positions (especially light elements) and thus serves as a critical probe for revealing microscopic structures in materials science. However, traditional Rietveld refinement of ND data relies heavily on manual operation of specialized software, which is time-consuming, labor-intensive, and highly dependent on user expertise, severely hindering automated analysis. The automation of Rietveld refinement has long been a long-standing and challenging problem in crystallography. To address this challenge, this paper presen"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Evaluation on five representative samples shows that the Rongzai agent achieves lower Rwp values than human specialists on three samples (2.88% vs. 4.42%, 5.06% vs. 5.40%, 7.60% vs. 9.00%), while on the other two samples its results are very close to those of the specialists.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The LLM can autonomously select and execute valid, non-overfitting refinement strategies across diverse samples using only the provided knowledge base and without introducing systematic bias or unphysical parameters.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"An LLM agent automates Rietveld refinement of neutron diffraction data and matches or beats human experts on Rwp fit quality for five test samples.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"An LLM-based agent autonomously refines neutron diffraction data and matches or beats human experts on fit quality.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"6375deec5dbbc39debdcf9f5d583b4f5b71ae16967d16fc97430b1574a3a0f86"},"source":{"id":"2605.13911","kind":"arxiv","version":1},"verdict":{"id":"377d400f-b18a-40e2-8c0e-86654cc16228","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T03:09:43.179159Z","strongest_claim":"Evaluation on five representative samples shows that the Rongzai agent achieves lower Rwp values than human specialists on three samples (2.88% vs. 4.42%, 5.06% vs. 5.40%, 7.60% vs. 9.00%), while on the other two samples its results are very close to those of the specialists.","one_line_summary":"An LLM agent automates Rietveld refinement of neutron diffraction data and matches or beats human experts on Rwp fit quality for five test samples.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The LLM can autonomously select and execute valid, non-overfitting refinement strategies across diverse samples using only the provided knowledge base and without introducing systematic bias or unphysical parameters.","pith_extraction_headline":"An LLM-based agent autonomously refines neutron diffraction data and matches or beats human experts on fit quality."},"references":{"count":19,"sample":[{"doi":"","year":null,"title":"Haberl, B., Guthrie, M., Boehler, R.: Advancing neutron diffraction for accurate structural measurement of light elements at megabar pressures13(1), 4741","work_id":"09f9d16e-7548-416e-b937-b9beec6611e3","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Pomjakushin, V., Plokhikh, I., White, J., Fujishiro, Y., Kanazawa, N., Tokura, Y., Pomjakushina, E.: Topological magnetic structures in MnGe: Neutron diffraction and symmetry analysis107(2), 024410","work_id":"abd084e8-f5df-4bc5-9874-ffb5f081874a","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Vershinina, T., Samoylova, N.Y., Sumnikov, S., Balagurov, A., Palacheva, V., Golovin, I.: Comparative study of structures and phase transitions in fe-(31-35) at% ga alloys by in situ neutron diffracti","work_id":"b0fbb6a6-b2df-44db-95e4-d0f22d036c4a","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"De Wolff, P.: On the determination of unit-cell dimensions from powder diffraction patterns10(9), 590–595","work_id":"cbf68f32-7f9c-49a1-ba65-dc84cc58066e","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Mighell, A.t., Santoro, A.: Geometrical ambiguities in the indexing of powder patterns8(3), 372–374","work_id":"c5ca747b-186b-488d-9ce5-b5aa7bb6dbb1","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":19,"snapshot_sha256":"ba0b2f4362308c66ed5ab112c933e79c267459083e8421d1140d58acc255ac45","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}