3 Search Results

Large language models (LLMs) show remarkable potential for scientific reasoning but often produce unreliable or scientifically unactionable outputs when faced with multi-step logic, domain grounding, and interpretability challenges, especially in complex fields like chemistry and materials science. Here, we introduce a framework of philosophical reasoning agents, inspired by canonical thinkers such as Socrates, Descartes, Kant, and Hume, to guide LLM behavior via structured prompt engineering. These agents embody distinct reasoning paradigms (dialectical inquiry, deductive logic, rule-based judgment, and empirical validation) and are evaluated across multiple chemistry subdomains, physical, analytical, general, inorganic, and organic chemistry, using the ChemBench benchmark. Our agenticmore » prompting approach yields substantial accuracy gains on open-ended numerical chemistry questions, with gains of +11.5 percentage points for GPT-4o with Hume, +4.5 percentage points for GPT-5 with Kant, and +21.8 percentage points for GPT-5.1 with Socrates at the strict 1% error threshold, relative to the corresponding base models. Beyond accuracy, we observe benchmark-level model–agent performance patterns, suggesting that different prompting styles interact differently with each base model. These findings demonstrate that embedding philosophy-of-science principles into multi-agent frameworks can improve and produce interpretable, adaptive, and domain-aligned scientific LLMs.« less

As large language models (LLMs) become central tools in science, improving their reasoning capabilities is critical for meaningful and trustworthy applications. We introduce a Socratic agent for scientific reasoning, implemented through a structured system prompt that guides LLMs via classical principles of inquiry. Unlike typical prompt engineering or retrieval-based methods, our approach leverages definition, analogy, hypothesis elimination, and other Socratic techniques to generate more coherent, critical, and domain-aware responses. We evaluate the agent across diverse scientific domains and benchmark it on the abstraction and reasoning corpus challenge dataset, achieving 97.15% under a fixed prompting protocol and without fine-tuning or externalmore » tools. Expert evaluation shows improved reasoning depth, clarity, and adaptability over conventional LLM outputs, suggesting that structured prompting rooted in philosophical reasoning can improve the scientific utility of language models.« less

Bipolar membrane (BPM) electrochemical processes are a promising platform for carbon dioxide (CO2) separations, but the molecular level thermodynamic and kinetic understanding of CO2-to-bicarbonate (HCO3-) transformation remain poorly understood. This study employs a multiscale computational approach to systematically explore the adsorption and reactive transformation of CO2 in five anion exchange ionomer systems. Classical molecular dynamics (MD) simulation results demonstrate that polymers with imidazolium groups significantly reduce CO2 diffusion and enhance (OH-)-CO2 interactions due to stronger electrostatic and pi-interactions. Compared to the commonly used quaternary ammonium ionomers, imidazolium-functionalized ionomers show improved CO2 proximity and interaction strength. Ab initio MD and densitymore » functional theory (DFT) calculations reveal that the benzyl-substituted imidazolium (IM-Ben) substantially reduces the energy barrier for HCO3- formation (similar to 72 meV lower) compared to the alkyl-substituted IM-nBu, while also mitigating imidazolium deprotonation under moderate hydration conditions. Transition state analysis shows IM-Ben forms more extensive hydrogen-bonding networks, which stabilize the transition state structure and contribute to a lower energy barrier for bicarbonate formation. These findings highlight the advantage of the adjacent benzyl moiety in enabling efficient CO2-to-bicarbonate transformation via hydrated hydroxide ion counterions, offering mechanistic insights and clear molecular design principles for optimizing anion exchange ionomers at bipolar membrane interfaces for electrochemical CO2 separation applications.« less