paper-with-me

홈 › Papers

Simulate, Reason, Decide: Scientific Reasoning with LLMs for Simulation-Driven Decision Making

2026-06-03 · Yuhan Yang, Ruipu Li, Alexander Rodríguez arxiv

Scientific simulators are increasingly being integrated into LLM-driven systems for high-stakes simulation-driven decision-making. However, existing frameworks primarily use LLMs to generate, calibrate, or execute simulators, treating them as black-box interfaces rather than as structured mechanistic systems that can be reasoned about. As a result, current approaches lack the ability to identify, represent, and reason about the assumptions and mechanisms underlying simulator behavior, limiting transparency, auditability, and decision justification. We introduce MechSim, a mechanism-grounded neuro-symbolic reasoning framework for executable scientific simulators. Unlike prior neuro-symbolic approaches that primarily reason over static symbolic structures, MechSim enables LLM agents to reason about the mechanisms, assumptions, and execution behavior of scientific simulators. Our framework represents simulators through a shared structured schema capturing assumptions, variables, mechanism dependencies, and execution traces. On top of this representation, LLM agents operate as constrained reasoning engines that generate structured, evidence-grounded explanations linking simulator outcomes to their underlying mechanisms. We evaluate our approach across multiple high-stakes domains and show that it improves mechanism-level explanation quality, simulator analysis, and downstream decision-making reliability.

📄 PDF Abstract BibTeX arXiv:2606.04505

Code (0)

등록된 구현이 없습니다.

Tasks

Decision Making

Similar Papers 제목 키워드 기반

Demystifying Scientific Problem-Solving in LLMs by Probing Knowledge and Reasoning

2025-08-26 · Alan Li, Yixin Liu, Arpan Sarkar, Doug Downey 외 arxiv

Scientific problem solving poses unique challenges for LLMs, requiring both deep domain knowledge and the ability to apply such knowledge through complex reasoning. While automated scientific reasoners hold great promise…

Advancing the Scientific Method with Large Language Models: From Hypothesis to Discovery

2025-05-22 · Yanbo Zhang, Sumeer A. Khan, Adnan Mahmud, Huck Yang 외

With recent Nobel Prizes recognising AI contributions to science, Large Language Models (LLMs) are transforming scientific research by enhancing productivity and reshaping the scientific method. LLMs are now involved in …

Experimental Design

On LLM-Based Scientific Inductive Reasoning Beyond Equations

2025-09-12 · Brian S. Lin, Jiaxin Yuan, Zihan Zhou, Shouli Wang 외 arxiv

As large language models (LLMs) increasingly exhibit human-like capabilities, a fundamental question emerges: How can we enable LLMs to learn the underlying patterns from limited examples in entirely novel environments a…

Scientific Logicality Enriched Methodology for LLM Reasoning: A Practice in Physics

2026-05-16 · Zhaoxin Yu, Nan Xu, Kun Chen, Jiahao Zhao 외 arxiv

With the continuous advancement of reasoning abilities in Large Language Models (LLMs), their application to scientific reasoning tasks has gained significant research attention. Current research primarily emphasizes boo…

Scientists' First Exam: Probing Cognitive Abilities of MLLM via Perception, Understanding, and Reasoning

2025-06-12 · Yuhao Zhou, Yiheng Wang, Xuming He, Ruoyao Xiao 외

Scientific discoveries increasingly rely on complex multimodal reasoning based on information-intensive scientific data and domain-specific expertise. Empowered by expert-level scientific benchmarks, scientific Multimoda…

AttributeMultimodal ReasoningVisual Question Answering (VQA)