# LLM-Guided Contextual Action Evaluation for Operational Decisions in Industrial Processes

arXiv: https://arxiv.org/abs/2608.24156 · HTML: https://mlsanity.com/paper/2608.24156/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 30 references that are in the map.
- First posted on arXiv 25 Aug 2026.

## Builds on (most cited first, 16 of 16)

- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning](https://mlsanity.com/paper/2302.02662/) (2023)
- [Reward Machines: Exploiting Reward Function Structure in Reinforcement Learning](https://mlsanity.com/paper/2010.03950/) (2020)
- [Guiding Pretraining in Reinforcement Learning with Large Language Models](https://mlsanity.com/paper/2302.06692/) (2023)
- [A Survey of Reinforcement Learning Informed by Natural Language](https://mlsanity.com/paper/1906.03926/) (2019)
- [Learning Action Representations for Reinforcement Learning](https://mlsanity.com/paper/1902.00183/) (2019)
- [Grounding Language to Entities and Dynamics for Generalization in Reinforcement Learning](https://mlsanity.com/paper/2101.07393/) (2021)
- [The Natural Language of Actions](https://mlsanity.com/paper/1902.01119/) (2019)
- [Control Industrial Automation System with Large Language Model Agents](https://mlsanity.com/paper/2409.18009/) (2024)
- [RLang: A Declarative Language for Describing Partial World Knowledge to Reinforcement Learning Agents](https://mlsanity.com/paper/2208.06448/) (2022)
- [Moving Forward by Moving Backward: Embedding Action Impact over Action Semantics](https://mlsanity.com/paper/2304.12289/) (2023)
- [From Detection to Action: Using LLM Agents for Fault-Tolerant Control](https://mlsanity.com/paper/2606.28011/) (2026)
- [Synthesizing Chemical Plant Operation Procedures using Knowledge, Dynamic Simulation and Deep Reinforcement Learning](https://mlsanity.com/paper/1903.02183/) (2019)
- [LLM-Guided Task-Semantic Field Factorization for Industrial Process Forecasting](https://mlsanity.com/paper/2607.06623/) (2026)

## Abstract (arXiv)

Industrial actor--critic methods usually represent continuous actions as anonymous numerical coordinates. They must therefore learn from limited interactions which process variables each action affects, in which direction, and after what delay. Fixed industrial documents already describe part of these relations, but their open-text statements neither represent the current operating condition nor directly fit a numerical policy. This article presents LLM-Guided Contextual Action Evaluation for Operational Decisions in Industrial Processes (LCAE), which uses a large language model before training to normalize fixed documents into a frozen action--observation--direction--delay relation basis. Recent numerical action--response history then modulates the current strength of each relation, while the evaluated action forms a state-conditioned nonlinear action-effect field in the same basis. The critic evaluates actions through this field, and the actor uses the same relation gains to generate actions, making document semantics part of maximum-entropy policy learning. Neither the LLM nor the embedding model runs online during training or deployment; the deployed policy uses only frozen semantic artifacts and visible numerical history. The method states a falsifiable hypothesis: when documented relations are correct and recent history reflects their contextual strength, this action representation should provide a more useful decision bias than raw action coordinates.