Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning

Hugging Face Daily Papers Papers
scientific-foundation-model structural-reasoning multimodal proteins molecules crystals interpretable-ai

Summary

SciReasoner is a multimodal scientific foundation model that enables interpretable structural reasoning across proteins, molecules, and crystals, achieving state-of-the-art performance on 67 out of 86 benchmarks.

Structure-property relationships are foundational to biology, chemistry and materials science, where function, reactivity and physical response emerge from spatial, chemical and periodic organization. Mechanistically explaining these relationships requires interpreting structural evidence through scientific principles and physical constraints, from stereochemistry and bonding to symmetry, energetics and periodic order. However, applying artificial intelligence to this process presents a joint challenge of representation and reasoning: models must preserve domain-native structural information while showing how specific evidence supports predictions under these constraints. Here we introduce SciReasoner, a multimodal scientific foundation model for native structural reasoning across proteins, small molecules and inorganic crystals. SciReasoner discretizes coordinates, topologies and periodic connectivities into a unified structure-aware vocabulary, treating structural tokens as addressable evidence units during reasoning. In homology-controlled Gene Ontology prediction, SciReasoner improves Cellular Component annotation for low-homology and orphan-like proteins, increasing F_{max} from 0.42 to 0.55. In chemistry, it raises single-step retrosynthesis accuracy from 0.63 to 0.72 while generating fragment-level disconnection and precursor-verification traces. In materials science, its representations separate elemental and compound phases and resolve high- and low-band-gap regimes. Across 86 benchmarks, SciReasoner achieves state-of-the-art performance on 67 tasks. Double-blind expert evaluation rates its reasoning traces as preferred or at least comparable to those of a frontier large language model in 98% of cases. By making structure an inspectable substrate for reasoning under scientific constraints, SciReasoner connects accurate prediction with interpretable scientific inference.
Original Article
View Cached Full Text

Cached at: 07/09/26, 07:50 AM

Paper page - Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning

Source: https://huggingface.co/papers/2607.07708 Published on Jul 8

#1 Paper of the day Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

SciReasoner is a multimodal scientific foundation model that enables interpretable structural reasoning across proteins, molecules, and crystals by discretizing structural elements into a unified vocabulary for enhanced prediction and scientific inference.

Structure-property relationships are foundational to biology, chemistry and materials science, where function, reactivity and physical response emerge from spatial, chemical and periodic organization. Mechanistically explaining these relationships requires interpreting structural evidence through scientific principles and physical constraints, from stereochemistry and bonding to symmetry, energetics and periodic order. However, applying artificial intelligence to this process presents a joint challenge of representation and reasoning: models must preserve domain-native structural information while showing how specific evidence supports predictions under these constraints. Here we introduce SciReasoner, amultimodal scientific foundation modelfor nativestructural reasoningacross proteins, small molecules and inorganic crystals. SciReasoner discretizes coordinates, topologies and periodic connectivities into a unified structure-aware vocabulary, treating structural tokens as addressable evidence units during reasoning. Inhomology-controlled Gene Ontology prediction, SciReasoner improves Cellular Component annotation for low-homology and orphan-like proteins, increasing F_{max} from 0.42 to 0.55. In chemistry, it raisessingle-step retrosynthesisaccuracy from 0.63 to 0.72 while generatingfragment-level disconnectionandprecursor-verification traces. In materials science, its representations separateelemental and compound phasesand resolvehigh- and low-band-gap regimes. Across 86 benchmarks, SciReasoner achieves state-of-the-art performance on 67 tasks.Double-blind expert evaluationrates itsreasoning tracesas preferred or at least comparable to those of a frontier large language model in 98% of cases. By making structure an inspectable substrate for reasoning under scientific constraints, SciReasoner connects accurate prediction with interpretable scientific inference.

View arXiv pageView PDFProject pageGitHub1Add to collection

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2607.07708 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2607.07708 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2607.07708 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

SCI-PRM: A Tool Aware Process Reward Model for Scientific Reasoning Verification

arXiv cs.AI

SCI-PRM introduces a tool-aware Process Reward Model for scientific reasoning, trained on the SCIPRM70K dataset featuring 'Chain-of-Tool' trajectories that interleave reasoning with scientific tool execution. It enables effective test-time scaling and serves as a dense reward signal in reinforcement learning, outperforming proprietary models like GPT-5-Mini on tool-calling steps across scientific benchmarks.

SciR: A Controllable Benchmark for Scientific Reasoning in LLMs

arXiv cs.AI

SciR is a new controllable benchmark for evaluating LLMs on scientific reasoning including deduction, induction, and causal abduction, with parametric control over extraction and inference difficulty. Tests show both axes degrade performance across models, with reasoning models like DeepSeek-R1 outperforming instruct models on inference.

Deep Reasoning in General Purpose Agents via Structured Meta-Cognition

arXiv cs.CL

This paper introduces Deep Reasoning, an inference-time approach that uses structured meta-reasoning to construct task-specific scaffolds for general-purpose agents. The proposed agent, Dolores, outperforms existing methods by distributing cognition across lower-load reasoning threads, reducing hallucinations and improving performance across multiple benchmarks.