{"slug": "simulate-reason-decide-scientific-reasoning-with-llms-for-simulation-driven", "title": "Simulate, Reason, Decide: Scientific Reasoning with LLMs for Simulation-Driven Decision Making", "summary": "Researchers introduced MechSim, a neuro-symbolic reasoning framework that enables large language model agents to analyze the mechanisms and assumptions underlying scientific simulators rather than treating them as black boxes. The framework represents simulators through a structured schema of variables, dependencies, and execution traces, allowing LLMs to generate evidence-grounded explanations linking outcomes to their underlying mechanisms. In evaluations across high-stakes domains, MechSim improved mechanism-level explanation quality, simulator analysis, and the reliability of downstream decision-making.", "body_md": "arXiv:2606.04505v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/simulate-reason-decide-scientific-reasoning-with-llms-for-simulation-driven", "canonical_source": "https://arxiv.org/abs/2606.04505", "published_at": "2026-06-04 04:00:00+00:00", "updated_at": "2026-06-04 04:17:36.511674+00:00", "lang": "en", "topics": ["large-language-models", "artificial-intelligence", "ai-agents", "ai-research", "ai-safety"], "entities": ["MechSim"], "alternates": {"html": "https://wpnews.pro/news/simulate-reason-decide-scientific-reasoning-with-llms-for-simulation-driven", "markdown": "https://wpnews.pro/news/simulate-reason-decide-scientific-reasoning-with-llms-for-simulation-driven.md", "text": "https://wpnews.pro/news/simulate-reason-decide-scientific-reasoning-with-llms-for-simulation-driven.txt", "jsonld": "https://wpnews.pro/news/simulate-reason-decide-scientific-reasoning-with-llms-for-simulation-driven.jsonld"}}