{"ID":3052340,"CreatedAt":"2026-06-04T04:41:36.695875263Z","UpdatedAt":"2026-06-06T06:34:39.340662719Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.04505","arxiv_id":"2606.04505","title":"Simulate, Reason, Decide: Scientific Reasoning with LLMs for Simulation-Driven Decision Making","abstract":"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.","short_abstract":"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 b...","url_abs":"https://arxiv.org/abs/2606.04505","url_pdf":"https://arxiv.org/pdf/2606.04505v1","authors":"[\"Yuhan Yang\",\"Ruipu Li\",\"Alexander Rodríguez\"]","published":"2026-06-03T06:36:51Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Large Language Model\"]","has_code":false}