Search papers, labs, and topics across Lattice.
This paper introduces MOF-Sleuth, a reinforcement-guided auditing agent designed to enhance the reliability of metal-organic framework (MOF) crystallographic information files (CIFs) by coupling chemical evidence with language model explanations. The tool comprises a Forensic Lab for deriving chemical evidence and a Sleuth reasoning engine that generates evidence-grounded explanations, addressing the dual challenges of fine-grained attribution and unreliable CIF reasoning. MOF-Sleuth achieves state-of-the-art performance across four benchmarks, significantly improving detection, attribution, and the quality of grounded explanations in CIF auditing.
MOF-Sleuth transforms CIF auditing by linking chemical evidence directly to language model explanations, achieving unprecedented accuracy and clarity in diagnosing structural errors.
Large metal-organic framework (MOF) databases support simulation, screening, and machine learning through crystallographic information files (CIFs). Subtle chemical and structural errors in these inputs can compromise downstream results and hinder manual inspection. LLM advances in computational chemistry offer paths beyond predictive screening toward fine-grained diagnosis with evidence-grounded explanations. However, two challenges remain: (i) limited fine-grained attribution: MOF-specific validators and machine-learning models scale detection but provide fixed checks, readiness scores, or coarse labels rather than evidence-grounded explanations; and (ii) unreliable CIF reasoning: direct LLM auditing is costly and unreliable because chemical evidence is implicit across atom-site records and requires geometric, connectivity, occupancy, and charge calculations. Both stem from weak coupling between chemical evidence and language-model explanation. We introduce MOF-Sleuth, a reinforcement-guided CIF auditing agent with two modules: a deterministic Forensic Lab and a Sleuth reasoning engine. The Lab derives composition, geometry, connectivity, occupancy, coordination, and charge evidence, and Sleuth uses this evidence to produce an evidence-grounded explanation, error types, and a binary decision. Reward-guided reinforcement learning (RL) turns tool measurements into chemical explanation-level supervision, rewarding not only the final answer but also cited chemical evidence and evidence-supported diagnoses. We introduce Chemically Grounded Diagnosis (Chem-GD), a metric that assesses whether a correct diagnosis is explained by factual, relevant CIF-derived evidence. Across four benchmarks, MOF-Sleuth establishes state-of-the-art performance among LLM-based approaches and MOF-specific machine-learning methods, demonstrating gains in detection, attribution, and grounded explanation quality.
