Chanyoung Park

The Second Workshop on SciSoc Agents & LLMs: Agentic AI for Scientific and Societal Advances aims to explore the emerging paradigm of agentic artificial intelligence, where Large Language Models (LLMs) are combined with autonomous agents, tools, memory, and multi-step reasoning to drive scientific discovery and address critical societal challenges. As LLMs continue to advance in capability, their integration into agent-based systems enables more interactive, goal-driven, and adaptive workflows that go beyond passive text generation. In particular, Agentic AI systems have demonstrated strong potential in orchestrating complex scientific pipelines, reasoning over large and heterogeneous datasets, interacting with external environments, and supporting decision-making in domains such as healthcare, environmental science, education, public policy, and social sciences. By bringing together researchers and practitioners from AI, data mining, science, and society, this workshop aims to foster a comprehensive understanding of how LLMs and agent-based architectures jointly redefine traditional research methodologies. Participants will explore novel agentic frameworks, multi-agent collaboration, and real-world deployments that leverage LLM-powered agents to accelerate scientific progress and generate meaningful societal impact.

Machine learning (ML) has seen promising developments in materials science, yet its efficacy largely depends on detailed crystal structural data, which are often complex and hard to obtain, limiting their applicability in real-world material synthesis processes. An alternative, using compositional descriptors, offers a simpler approach by indicating the elemental ratios of compounds without detailed structural insights. However, accurately representing materials solely with compositional descriptors presents challenges due to polymorphism, where a single composition can correspond to various structural arrangements, creating ambiguities in its representation. To this end, we introduce PCRL, a novel approach that employs probabilistic modeling of composition to capture the diverse polymorphs from available structural information. Extensive evaluations on sixteen datasets demonstrate the effectiveness of PCRL in learning compositional representation, and analysis on model uncertainty highlights its potential applicability of PCRL in material discovery.

Lipid Nanoparticles (LNPs) are widely used as delivery systems for nucleic acid therapeutics, where transfection efficiency is determined by both the identities of constituent lipid components and their composition ratios. While prior studies have focused on learning molecular representations for individual components, modeling how multiple components and their ratios jointly influence LNP performance remains underexplored. In this work, we propose STRATA, a framework that models molecule interaction between LNP components, which is known to contribute to LNP transfection efficiency. Our approach is built on two complementary views: (1) a ratio-centric view that captures interaction patterns induced by composition ratios through a transformer with a Ratio-induced Positional Embedding, and (2) a molecule-centric view that incorporates interaction-induced effects into structure-based molecule embeddings. By jointly training and aligning these views, our model integrates molecular structure and composition ratio within a unified framework that captures interaction-driven effects. Experiments demonstrate that our method improves prediction accuracy and generalization to unseen molecules and ratios, highlighting the effectiveness of our approach.