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

Researchers have introduced MechSim, a novel neuro-symbolic reasoning framework that enables LLMs to understand and explain the underlying mechanisms of scientific simulators. This approach enhances transparency and reliability in high-stakes simulation-driven decision-making.

Computer Science > Artificial Intelligence

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

View PDF HTML (experimental)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.

Bibliographic and Citation Tools

Code, Data and Media Associated with this Article

Demos

Recommenders and Search Tools

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Source: arXiv cs.AI Recent

More in this category

agentic-systems

Not All Errors Are Equal: Consequence-Aware Reasoning Compute Allocation

Current reasoning models allocate compute based on task difficulty, assuming all failures cost the same. This paper proposes a consequence-aware allocation method that routes higher-consequence tasks to larger compute budgets, reducing cost-weighted loss by 22% to 33%.

agentic-systems

Cascading Hallucination in Agentic RAG: The CHARM Framework for Detection and Mitigation

Researchers have introduced CHARM, a breakthrough architectural framework designed to detect and mitigate "cascading hallucinations" in Agentic RAG systems, reducing error propagation by 82.1%.

agentic-systems

The Digital Apprentice: A Framework for Human-Directed Agentic AI Development

Researchers have proposed 'Digital Apprentice', a framework for scalable and safe agentic AI where autonomy is earned through human guidance. This framework addresses the fundamental tension between AI scalability and accountability.

agentic-systems

AgentJet: A Flexible Swarm Training Framework for Agentic Reinforcement Learning

Researchers have introduced AgentJet, a breakthrough distributed swarm training framework for LLM agent reinforcement learning. Featuring a decoupled multi-node architecture, AgentJet optimizes performance and enables autonomous, large-scale AI research without human intervention.

agentic-systems

Beyond Prompt-Based Planning: MCP-Native Graph Planning-based Biomedical Agent System

BioManus is an MCP-native biomedical agent system that leverages graph-scaffolded planning to automate complex bioinformatics workflows, significantly improving execution accuracy and context efficiency.

agentic-systems

Trivium: Temporal Regret as a First-Class Objective for Causal-Memory Controllers

Researchers propose Trivium, a framework introducing 'temporal regret' as a core objective to prevent AI agents from repeating past mistakes. By systematically logging and correcting the 'why' and 'when' of failures, Trivium enables LLM agents to self-correct via external causal models without retraining weights.

EXPLORE TOPICS