# Simulator-Grounded Large Language Models for Industrial Causal Reasoning: Tool-Use, Structured Injection, and Plant-Portable Retrieval for Wastewater Treatment Decision Support

arXiv: https://arxiv.org/abs/2608.05151 · HTML: https://mlsanity.com/paper/2608.05151/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Causal reasoning in LLMs, one of 17 directions in LLM reasoning.
- Builds on 30 of its 99 references that are in the map.
- First posted on arXiv 20 May 2026.

## Placed in

- LLM reasoning / [Causal reasoning in LLMs](https://mlsanity.com/lr/causal-reasoning-in-llms/)

## Builds on (most cited first, 30 of 30)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [PaLM 2 Technical Report](https://mlsanity.com/paper/2305.10403/) (2023)
- [REPLUG: Retrieval-Augmented Black-Box Language Models](https://mlsanity.com/paper/2301.12652/) (2023)
- [Galactica: A Large Language Model for Science](https://mlsanity.com/paper/2211.09085/) (2022)
- [An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning](https://mlsanity.com/paper/2308.08747/) (2023)
- [Textbooks Are All You Need](https://mlsanity.com/paper/2306.11644/) (2023)
- [LoRA Learns Less and Forgets Less](https://mlsanity.com/paper/2405.09673/) (2024)
- [MEDITRON-70B: Scaling Medical Pretraining for Large Language Models](https://mlsanity.com/paper/2311.16079/) (2023)
- [TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables](https://mlsanity.com/paper/2402.19072/) (2024)
- [TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Series](https://mlsanity.com/paper/2308.08241/) (2023)
- [Understanding Catastrophic Forgetting in Language Models via Implicit Inference](https://mlsanity.com/paper/2309.10105/) (2023)
- [Internet-augmented language models through few-shot prompting for open-domain question answering](https://mlsanity.com/paper/2203.05115/) (2022)
- [Chatlaw: A Multi-Agent Legal Assistant based on a Role-Aligned Mixture-of-Experts Architecture](https://mlsanity.com/paper/2306.16092/) (2023)
- [Multiple Physics Pretraining for Physical Surrogate Models](https://mlsanity.com/paper/2310.02994/) (2023)
- [Text-to-LoRA: Instant Transformer Adaption](https://mlsanity.com/paper/2506.06105/) (2025)
- [Autonomous Control Leveraging LLMs: An Agentic Framework for Next-Generation Industrial Automation](https://mlsanity.com/paper/2507.07115/) (2025)
- [Knowledge Graph Fusion with Large Language Models for Accurate, Explainable Manufacturing Process Planning](https://mlsanity.com/paper/2506.13026/) (2025)
- [SimulCost: A Cost-Aware Benchmark and Toolkit for Automating Physics Simulations with LLMs](https://mlsanity.com/paper/2603.20253/) (2026)
- [Large Language Models for Water Distribution Systems Modeling and Decision-Making](https://mlsanity.com/paper/2503.16191/) (2025)
- [Systematic Integration of Digital Twins and Constrained LLMs for Interpretable Cyber-Physical Anomaly Detection](https://mlsanity.com/paper/2604.03790/) (2026)
- [Data-Driven Open-Loop Simulation for Digital-Twin Operator Decision Support in Wastewater Treatment](https://mlsanity.com/paper/2604.20935/) (2026)
- [Brainstacks: Cross-Domain Cognitive Capabilities via Frozen MoE-LoRA Stacks for Continual LLM Learning](https://mlsanity.com/paper/2604.01152/) (2026)
- [WaterAdmin: Orchestrating Community Water Distribution Optimization via AI Agents](https://mlsanity.com/paper/2604.10343/) (2026)
- [Explainable Wastewater Digital Twins: Adaptive Context-Conditioned Structured Simulators with Self-Falsifying Decision Support](https://mlsanity.com/paper/2605.19826/) (2026)

## Abstract (arXiv)

Wastewater operators need answers grounded in how their plant's variables interact and how fast effects propagate, not in generic pretraining text, when asking causal questions such as "why is N2O rising?" or "what happens if I cut aeration by 20%?". We compare three concrete ways to ground a frozen Qwen2.5-32B-Instruct model in an architecturally interpretable wastewater simulator (CCSS-IX): a live simulator oracle (Method 1), structured parameter injection (Method 2), and a Decoupled Recall-Reasoning (DRR) retriever (Method 3). On a 198-question causal benchmark the three reach 99.5%, 79%, and 75.8%, forming a deployment ladder above the strongest retrieval-augmented baseline at 48%. The DRR retriever has 110M parameters and trains per plant in ~17 seconds; after cross-plant transfer to a biologically distinct plant it still reaches 88%, while Method 2's static table cannot transfer. On a 60-question counterfactual benchmark only Method 3 handles queries about what happens after an intervention: +16.3 pp over Method 2, paired 95% CI [+7.1, +26.4] pp, with 100% on the timescale and operating-regime categories. On the AI2 Reasoning Challenge (ARC) with an OpenBookQA fact corpus, the same selective-retrieval mechanism reaches 79% versus unconstrained Llama-3.1-8B 76% and full-injection 74%, a +3 pp out-of-domain replication that argues against a result specific to wastewater treatment. We provide the first single-simulator comparison of live tool-use, static parameter injection, and learned numerical-parameter retrieval for industrial causal question answering.