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

arXiv: https://arxiv.org/abs/2606.04505 · HTML: https://mlsanity.com/paper/2606.04505/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 22 of its 67 references that are in the map.
- First posted on arXiv 3 Jun 2026.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 22 of 22)

- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [Graph of Thoughts: Solving Elaborate Problems with Large Language Models](https://mlsanity.com/paper/2308.09687/) (2023)
- [ERASER: A Benchmark to Evaluate Rationalized NLP Models](https://mlsanity.com/paper/1911.03429/) (2019)
- [Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning](https://mlsanity.com/paper/2305.12295/) (2023)
- [ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models](https://mlsanity.com/paper/2404.07738/) (2024)
- [TradingAgents: Multi-Agents LLM Financial Trading Framework](https://mlsanity.com/paper/2412.20138/) (2024)
- [MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Making](https://mlsanity.com/paper/2404.15155/) (2024)
- [Towards End-to-End Automation of AI Research](https://mlsanity.com/paper/2606.15497/) (2026)
- [Causal Parrots: Large Language Models May Talk Causality But Are Not Causal](https://mlsanity.com/paper/2308.13067/) (2023)
- [GenSim: Generating Robotic Simulation Tasks via Large Language Models](https://mlsanity.com/paper/2310.01361/) (2023)
- [Curie: Toward Rigorous and Automated Scientific Experimentation with AI Agents](https://mlsanity.com/paper/2502.16069/) (2025)
- [Causal-Copilot: An Autonomous Causal Analysis Agent](https://mlsanity.com/paper/2504.13263/) (2025)
- [A Probabilistic Framework for LLM-Based Model Discovery](https://mlsanity.com/paper/2602.18266/) (2026)
- [Agent Trading Arena: A Study on Numerical Understanding in LLM-Based Agents](https://mlsanity.com/paper/2502.17967/) (2025)
- [G-Sim: Generative Simulations with Large Language Models and Gradient-Free Calibration](https://mlsanity.com/paper/2506.09272/) (2025)
- [Context, Composition, Automation, and Communication -- The C2AC Roadmap for Modeling and Simulation](https://mlsanity.com/paper/2310.05649/) (2023)
- [AI Agents as Policymakers in Simulated Epidemics](https://mlsanity.com/paper/2601.04245/) (2026)
- [SimulRAG: Simulator-based RAG for Grounding LLMs in Long-form Scientific QA](https://mlsanity.com/paper/2509.25459/) (2025)
- [Agentic Framework for Epidemiological Modeling](https://mlsanity.com/paper/2602.00299/) (2026)

## Abstract (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.