arXiv:2608. 04170v1 Announce Type: cross Abstract: AI co-scientists can generate fluent materials-science hypotheses, but fluency does not show that an answer preserves a scientifically meaningful mechanism.
arXiv:2607. 00924v1 Announce Type: new Abstract: Accelerating materials discovery requires AI systems that can generate scientifically valid hypotheses through multi-step, domain-grounded reasoning.
ReactBench is a benchmark designed to evaluate the structural reasoning abilities of multimodal large language models (MLLMs) using chemical reaction diagrams. The dataset contains 1,618 expert‑annotated question‑answer pairs that test reasoning across four hierarchical task dimensions, from simple endpoint counting to complex topological analysis. Evaluation of 24 MLLMs shows a performance gap of more than 30% between anchor‑based tasks and holistic structural reasoning tasks, indicating that current models struggle with reasoning over branching, converging, and cyclic structures.
arXiv:2606. 18874v1 Announce Type: new Abstract: AI systems can increasingly automate scientific workflows, but the reasoning that links prior evidence, generated ideas, experiments and final claims often remains implicit inside model inference.
arXiv:2607. 17917v1 Announce Type: new Abstract: Scientific Reasoning Graph Extraction (SRGE) aims to recover explicit links among observations, evidence, intermediate claims, and paper-level conclusions.
Multimodal large language models (MLLMs) are increasingly explored as interfaces for scientific image analysis, where a visual question-answering (VQA) response may be paired with a spatial output tha...
SynAgent is a framework that uses large language model agents to run autonomous experiments while building an explicit, revisable understanding of the synthesis process. Unlike traditional black‑box optimizers, SynAgent generates analysis skills on the fly and reasons multimodally over data such as X‑ray diffraction patterns and electron micrographs. In an 18‑experiment campaign on LiCoO₂ thin‑film deposition, SynAgent produced highly crystalline films and uncovered a sharp temperature threshold and optimal growth window (650–690 °C) for crystallization.
The paper introduces the Procedural Graph, a framework that structures procedural knowledge into (procedure, relation, procedure) triplets to guide large language model agents in planning and tool usage. At each decision point, a guidance model uses the local subgraph to bias the agent’s next action, while an LLM refiner self‑evolves the graph by editing its topology based on successful versus failed trajectories. Experiments across datasets and LLMs show that Procedural Graphs consistently outperform memory‑based baselines, and the self‑evolution mechanism further improves performance without manual engineering.
The paper introduces Procedural Graphs, a framework that structures procedural knowledge for large language model agents as (procedure, relation, procedure) triplets, analogous to knowledge graphs for factual data. At each decision point, a guidance model uses the local subgraph to bias the agent’s next action, while an LLM refiner self‑evolves the graph by comparing failed and successful trajectories, editing its topology to improve performance. Experiments across various datasets, tasks, and LLMs show that Procedural Graphs consistently outperform memory‑based baselines, and the self‑evolution mechanism further enhances results without manual engineering.
arXiv:2609.24470v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are increasingly explored as interfaces for scientific image analysis, where a visual question-answering (VQA)...
Self-driving laboratories can explore synthesis conditions autonomously, but their decision-making layer is typically a black-box optimizer, and the output is a set of optimized samples, with the meas...
The paper introduces AutoMat, a benchmark designed to test large language model (LLM) coding agents on their ability to reproduce claims from computational materials science. AutoMat presents three challenges: reconstructing underspecified procedures, navigating specialized toolchains, and assessing whether the evidence supports a claim. Experiments show that current LLM agents achieve low success rates, with the best setting reaching only 53%, and failures stem mainly from incomplete procedures, methodological deviations, and execution fragility.
arXiv:2607. 14658v1 Announce Type: new Abstract: While Multimodal Large Language Models (MLLMs) excel in general tasks, rigorous scientific reasoning remains challenging due to the limitations of monolithic, linear planning.