Skip to content

cgcui/LLM4Control

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 

Repository files navigation

🤖 Awesome LLM for Control (LLM4Control)

A curated, living collection of papers, frameworks, and resources at the intersection of Large Language Models (LLMs) and Control Systems / Power Electronics.

As LLMs demonstrate emergent reasoning and planning capabilities, their integration with rigorous control theory—from classical PID design to nonlinear optimal control and power electronics—is rapidly evolving. This repository tracks the frontier.


📖 Table of Contents

Category # Papers
📚 Surveys & Reviews 15
🔧 LLM for Control & Power Electronics Design 32
🤝 LLM Agents & Multi-Agent Systems 13
🎮 RL / DRL for Control 6
🔮 Symbolic & Interpretable Control Policies 17
🧠 Meta-Learning for Adaptive Control 4
⚡ Power Electronics (Classical & Data-Driven) 9
🔬 AI for Scientific Discovery 4
📦 Other 41

📚 Surveys & Reviews

Comprehensive surveys covering LLMs, RL, and AI methods for control systems and power electronics.

Title Authors Year Venue TL;DR
When {{Control Meets Large Language Models Nosrati, Komeil, Tepljakov, Aleksei, Belikov, Juri et al. 2026 Explores the bidirectional relationship between LLMs and control: how LLMs advance control design while control theory helps improve LLM alignment and interpretability.
{{LLM and AI Agents 2026 A comprehensive survey on LLM and AI agents for autonomous systems, covering the transition from modular rule-based to reasoning-driven agent-based approaches.
Synthesizing {{Interpretable Control Policies Bosio, Carlo, Mueller, Mark W. 2026 The combination of Large Language Models (LLMs), systematic evaluation, and evolutionary algorithms has enabled breakthr...
Using {{Large Language Models Ouhib, Lamia 2026 The integration of Large Language Models (LLMs) into control system design has evolved rapidly from basic prompt-based e...
Large {{Language Models Bernadić, Alen, Kujundžić, Goran, Primorac, Ivana 2025 International Journal of Innovative Solutions in E It is suggested that LLMs can significantly enhance the efficiency and reliability of power system operations, paving the way for more intelligent and adaptive energy management systems.
Multi-{{Agent Collaboration Mechanisms Tran, Khanh-Tung, Dao, Dung, Nguyen, Minh-Duong et al. 2025 This work provides an extensive survey of the collaborative aspect of MASs and introduces an extensible framework to guide future research, and identifies key lessons learned, open challenges, and potential research directions of MASs towards artificial collective intelligence.
Empowering Scientific Discovery with Explainable Small Domain-Specific and Large Language Models Yu, Hengjie, Wang, Yizhi, Cheng, Tao et al. 2025 Artificial Intelligence Review As artificial intelligence (AI) increasingly integrates into scientific research, explainability has become a cornerston...
Exploring the Role of Large Language Models in the Scientific Method: From Hypothesis to Discovery Zhang, Yanbo, Khan, Sumeer A., Mahmud, Adnan et al. 2025 npj Artificial Intelligence For LLMs to serve as relevant and effective creative engines and productivity enhancers, their deep integration into all steps of the scientific process should be pursued in collaboration and alignment with human scientific goals, with clear evaluation metrics.
A {{Review Chen, Peng, Zhao, Jianfeng, Liu, Kangli et al. 2024 IEEE Transactions on Industry Applications This article provides a summary of existing published research papers on reinforcement learning control for power electronic converters, and introduces the existing RL control strategies for various power electronic converter topologies.
{{MapCoder Islam, Md Ashraful, Ali, Mohammed Eunus, Parvez, Md Rizwan 2024 A new approach to code generation tasks leveraging multi-agent prompting that uniquely replicates the full cycle of program synthesis as observed in human developers, and consistently delivers superior performance across various programming languages and varying problem difficulties.
A Survey on {{LLM-based Li, Xinyi, Wang, Sai, Zeng, Siqi et al. 2024 Vicinagearth A comprehensive survey of LLM-based multi-agent systems is presented, offering a systematic review of these studies, and a general structure encompassing five key components: profile, perception, self-action, mutual interaction, and evolution is synthesized.
A {{Review Núñez-Molina, Carlos, Mesejo, Pablo, Fernández-Olivares, Juan 2024 ACM Comput. Surv. This article reviews AP, RL and hybrid methods for solving Sequential Decision Processes (SDPs), focusing on their knowledge representation: symbolic, subsymbolic, or a combination, and concludes that neurosymbolic AI poses a promising approach for SDM, since it combines AP and RL with a hybrid knowledge representation.
Mathematical Discoveries from Program Search with Large Language Models Romera-Paredes, Bernardino, Barekatain, Mohammadamin, Novikov, Alexander et al. 2024 Nature This work introduces FunSearch (short for searching in the function space), an evolutionary procedure based on pairing a pretrained LLM with a systematic evaluator that demonstrates the effectiveness of this approach to surpass the best-known results in important problems, pushing the boundary of existing LLM-based approaches.
Applying {{Large Language Models Xia, Yuchen, Jazdi, Nasser, Weyrich, Michael 2024 atp magazin The studies illustrate the ability of LLMs to manage versatile tasks and interface with digital twins and automation systems, indicating that efficiency and productivity improvements can be achieved by strategically deploying LLM technologies in industrial settings.
Deep {{Reinforcement Learning Li, Yuanzheng, Yu, Chaofan, Shahidehpour, Mohammad et al. 2023 Proceedings of the IEEE This article presents a comprehensive literature survey on DRL and its applications in smart grid operations, and reviews various DRL techniques as well as their extensions developed to cope with emerging issues in the smart grid, including optimal dispatch, operational control, electricity market, and other emerging areas.

🔧 LLM for Control & Power Electronics Design

Papers applying LLMs directly to controller synthesis, PID/H∞ tuning, power converter design, and automation.

Title Authors Year Venue TL;DR
When Control Meets Large Language Models: {{From Nosrati, Komeil, Tepljakov, Aleksei, Belikov, Juri et al. 2026 While large language models (LLMs) are transforming engineering and technology through enhanced control capabilities and...
{{ControlAgent Guo, Xingang, Keivan, Darioush, Syed, Usman et al. 2025 Control system design is a crucial aspect of modern engineering with far-reaching applications across diverse sectors in...
Crucible: {{Quantifying Jia, Lianchen, Li, Chaoyang, Houde, Qian et al. 2025 This work introduces Crucible, an agent that employs an LLM-driven, multi-level expert simulation to turn algorithms and defines a formalized metric to quantitatively evaluate their Tuning Potential, providing a new dimension for algorithm analysis and design.
{{LLM-based PID Kamenko, Ilija, Ilic, Slobodan, Congradac, Velimir 2025 2025 10th {{International Conference This study explores the application of Large Language Models (LLMs) to optimize Proportional-Integral-Derivative (PID) c...
Linear {{Feedback Control Systems Karn, Rupesh Raj 2025 This paper presents a novel approach that draws parallels between the iterative prompt optimization process in LLMs and feedback control systems, providing a mathematical foundation for integrating linear feedback control mechanisms with LLMs.
From {{Natural Language Li, Shihao, Li, Jiachen, Xu, Jiamin et al. 2025 We present textsc\S2C\ (Specification-to-Certified-Controller), a multi-agent framework that maps natural-language requi...
Towards {{Ethical AI Lin, Fanfan, Wilson, Peter, Li, Xinze et al. 2025 Artificial intelligence (AI) is rapidly transforming power electronics, with AI-related publications in IEEE Power Elect...
Automating the Practice of Science: {{Opportunities Musslick, Sebastian, Bartlett, Laura K., Chandramouli, Suyog H. et al. 2025 By discussing the motivations behind automated science, analyzing the hurdles encountered, and examining its implications, this article invites researchers, policymakers, and stakeholders to navigate the rapidly evolving frontier of automated scientific practice.
{{AgenticControl Narimani, Mohammad, Emami, Seyyed Ali 2025 Traditional control system design, reliant on expert knowledge and precise models, struggles with complex, nonlinear, or...
{{SmartControl Tohma, Kadir, Okur, Halil İbrahim, Gürsoy-Demir, Handan et al. 2025 SoftwareX SmartControl is an interactive PID controller design tool powered by the novel integration of Large Language Model (LLM)...
{{LLM-Agent-Controller Zahedifar, Rasoul, Mirghasemi, Sayyed Ali, Baghshah, Mahdieh Soleymani et al. 2025 This study presents the LLM-Agent-Controller, a multi-agent large language model (LLM) system developed to address a wid...
{{LLM-controller Zahedifar, Rasoul, Soleymani Baghshah, Mahdieh, Taheri, Alireza 2025 Robotics and Autonomous Systems In this study, a dynamic adaptation of a robot controller is investigated using large language models (LLMs). We propose...
{{LLMs-guided Zhou, Zhongchao, Lu, Yuxi, Zhu, Yaonan et al. 2025 With rapid advances in code generation, reasoning, and problem-solving, Large Language Models (LLMs) are increasingly ap...
Large {{Language Models Dharmaji, Rahul 2024 This manuscript is comprised of two sections — automated code generation for Programmable Logic Controllers and vulnerab...
{{ControlAgent Guo, Xingang, Keivan, Darioush, Syed, Usman Ahmed et al. 2024 Control system design is a crucial aspect of modern engineering with far-reaching applications across diverse sectors, i...
Design {{Automation Hermanns, Kevin 2024 {{CIPS The demand for power electronic solutions is growing rapidly. The number of skilled workers available in the labour mark...
Controller {{Design Automation Li, Wanrong, Li, Sinan, Yuan, Huawei et al. 2024 IEEE Transactions on Power Electronics Efficient tools for automating controller design are essential to meet the growing demands of power electronics (PE) app...
{{PE-GPT Lin, Fanfan, Li, Xinze, Lei, Weihao et al. 2024 IEEE Transactions on Industrial Electronics This study presents a pioneering approach to establish a multimodal LLM tailored for PE design applications, named PE-GPT, and proposes a hybrid framework that integrates an LLM agent with metaheuristic algorithms, Model Zoo, and Simulation Repository to enhance its multimodal processing capabilities and enables integration into the existing design workflow.
Physics-{{Informed LLM-Agent Liu, Junhua, Lin, Fanfan, Li, Xinze et al. 2024 LLM-based autonomous agents have demonstrated outstanding performance in solving complex industrial tasks. However, in t...
Using {{ChatGPT Liu, Quanrui, Yuan, Xibo, Busquets-Monge, Sergio et al. 2024 2024 {{IEEE Two customized generative pre-trained transformers are developed with a retrieval-augmented generation (RAG) framework to select the optimal topology and design the system's parameters with the predefined specifications.
Eureka: {{Human-Level Reward Design Ma, Yecheng Jason, Liang, William, Wang, Guanzhi et al. 2024 Eureka is presented, a human-level reward design algorithm powered by LLMs that exploits the remarkable zero-shot generation, code-writing, and in-context improvement capabilities of state-of-the-art LLMs to perform evolutionary optimization over reward code.
Autonomous {{Industrial Control Vyas, Javal, Mercangöz, Mehmet 2024 An innovative approach to industrial automation is proposed, introducing validation and reprompting architectures utilizing large language model (LLM)-based autonomous control agents that enables autonomous management of control tasks, adapting to unforeseen disturbances without human intervention.
{{LLM-Powered Multi-Actor System Xavier, Midhun, Laikh, Tatiana, Patil, Sandeep et al. 2024 {{IECON An innovative multiactor framework that harnesses the potential of LLMs to augment the functionalities of ICS by integrating conversational AI technologies, significantly improves human-machine interactions, enabling sophisticated analysis and visualization of intricate data sets.
Automated {{Companion Tool Zhetessov, Aidar, Venkataramanan, Prof. Giri 2024 2024 {{IEEE Energy Conversion Congress Due to their inherent nonlinearity, time-variance, system uncertainties, and requirements of robustness, control of powe...
Efficient and {{Robust Controller Design Automation Li, Wanrong, Li, Sinan, Yuan, Huawei et al. 2023 2023 {{IEEE Energy Conversion Congress The global penetration of power electronics (PE) has increased significantly, creating a pressing need for efficient and...
Towards Autonomous System: Flexible Modular Production System Enhanced with Large Language Model Agents Xia, Yuchen, Shenoy, Manthan, Jazdi, Nasser et al. 2023 2023 {{IEEE A novel framework that combines large language models (LLMs), digital twins and industrial automation system to enable intelligent planning and control of production processes and demonstrates how the implemented prototype can handle un-predefined tasks, plan a production process, and execute the operations.

🤝 LLM Agents & Multi-Agent Systems

Multi-agent LLM frameworks for autonomous control, industrial automation, and planning.

Title Authors Year Venue TL;DR
Learning Environment and Dynamics Representations for Autonomous Robot Navigation - ProQuest 2026 Explore millions of resources from scholarly journals, books, newspapers, videos and more, on the ProQuest Platform....
Towards an {{AI Gottweis, Juraj, Weng, Wei-Hung, Daryin, Alexander et al. 2025 Scientific discovery relies on scientists generating novel hypotheses that undergo rigorous experimental validation. To ...
Towards {{Agentic AI Huang, Lifu, Koutra, Danai, Kulkarni, Adithya et al. 2025 Companion {{Proceedings AI models for science [14] have the potential to harness large datasets, accelerate scientific discoveries and transform...
Al-{{Khwarizmi Mower, Christopher E., Bou-Ammar, Haitham 2025 Al-Khwarizmi is introduced, a novel agentic framework for physical law discovery from data, which integrates foundational models with SINDy and demonstrates state-of-the-art performance compared to alternatives, reaching a 20 percent increase against the best-performing alternative.
Discovering State-of-the-Art Reinforcement Learning Algorithms Oh, Junhyuk, Farquhar, Greg, Kemaev, Iurii et al. 2025 Nature It is shown that it is possible for machines to discover a state-of-the-art RL rule that outperforms manually-designed rules, and suggest that the RL algorithms required for advanced artificial intelligence may soon be automatically discovered from the experiences of agents, rather than manually designed.
{{DrAgent Saha, Barun Kumar, V, Aarthi, Naidu, O. D. 2025 2025 {{International Conference The results of performance evaluation indicate that DrAgent, in general, can significantly improve the accuracy of responses requiring numerical results, and the step-by-step reasoning of agentic workflow can potentially help power grid operators, both novice and expert, to learn or verify the process.
Towards Agentic Science for Advancing Scientific Discovery Xin, Hongliang, Kitchin, John R., Kulik, Heather J. 2025 Nature Machine Intelligence Artificial intelligence is transforming scientific discovery through (semi-)autonomous agents capable of reasoning, plan...
{{V2V-LLM Chiu, Hsu-kuang, Hachiuma, Ryo, Wang, Chien-Yi et al. 2025 ICRA 2026 First to integrate multimodal LLMs into V2V cooperative autonomous driving, proposing V2V-QA dataset and V2V-LLM model for cooperative perception and planning.
Autonomous {{Code Evolution Meets NP-Completeness Yu, Cunxi, Liang, Rongjian, Ho, Chia-Tung et al. 2025 Large language models (LLMs) have recently shown strong coding abilities, enabling not only static code generation but a...
{{MetaGPT Hong, Sirui, Zhuge, Mingchen, Chen, Jiaqi et al. 2024 MetaGPT is introduced, an innovative framework that incorporates efficient human workflows as a meta programming approach into LLM-based multi-agent collaboration and leverages the assembly line paradigm to assign diverse roles to various agents, thereby establishing a framework that can effectively and cohesively deconstruct complex multi- agent collaborative problems.
Meta-{{Learning Augmented MPC Lapandić, Dženan, Xie, Fengze, Verginis, Christos K. et al. 2024 IEEE Control Systems Letters A major challenge in autonomous flights is unknown disturbances, which can jeopardize safety and cause collisions, espec...

🎮 RL / DRL for Control

Reinforcement and deep reinforcement learning applied to power converters, smart grids, and robotic control.

Title Authors Year Venue TL;DR
Reinforcement {{Learning-Based Control Weber, Daniel, Lange, Jarren, Wallscheid, Oliver 2026 IEEE Journal of Emerging and Selected Topics in In Reinforcement learning-based control allows a model-free, self-adaptive control approach with the possibility of non-lin...
{{TransformerMPC Zinage, Vrushabh, Khalil, Ahmed, Bakolas, Efstathios 2024 Proposes TransformerMPC that uses Transformer attention mechanism to accelerate Model Predictive Control (MPC) by removing inactive constraints and providing better warm-start initialization, achieving up to 35x speedup.
Discovering {{Symbolic Policy Kim, Soo Kyung, Song, Chihyeon, Chen, Weizhe et al. 2023 IFAC-PapersOnLine We propose a learning framework for interpretable HVAC control in buildings using deep reinforcement learning (DRL). Our...
A {{Model-Free Switching Qashqai, Pouria, Babaie, Mohammad, Zgheib, Rawad et al. 2023 IEEE Access A novel model-free switching and control method for three-level neutral point clamped (NPC) converter using deep reinforcement learning (DRL), which exhibits superior adaptability to real-time changes and uncertainties, delivering more robust performance compared to similar conventional methods like MPC.
Discovering Symbolic Policies with Deep Reinforcement Learning Landajuela, Mikel, Petersen, Brenden K., Kim, Sookyung et al. 2021 Proceedings of the 38th {{International Conference Deep reinforcement learning (DRL) has proven successful for many difficult control problems by learning policies represe...

🔮 Symbolic & Interpretable Control Policies

Discovering interpretable policies: symbolic regression, decision trees, Lyapunov functions, explainable RL.

Title Authors Year Venue TL;DR
{{Neural Optimization Machine Li, Anran, Swensen, John P., Hosseinzadeh, Mehdi 2025 Proposes a Neural Optimization Machine (NOM) that transforms non-convex optimization problems in NN-based optimal control into neural network training problems with rigorous stability guarantees.
Deep {{Symbolic Optimization Hayes, Conor F., Silva, Felipe Leno Da, Yang, Jiachen et al. 2025 This chapter provides a comprehensive overview of the DSO framework and illustrates its transformative potential for automating symbolic optimization in scientific discovery.
Constructive {{Symbolic Reinforcement Learning Patrascu, Andrei T. 2025 A novel learning and planning framework that replaces traditional reward-based optimisation with constructive logical inference and presents a new direction for reinforcement learning grounded not in numeric optimisation, but in constructive logic and proof theory.
{{SkillTree Wen, Yongyan, Li, Siyuan, Zuo, Rongchang et al. 2025 Proceedings of the AAAI Conference on Artificial I Deep reinforcement learning (DRL) has achieved remarkable success in various domains, yet its reliance on neural network...
Model-Free Robust Underactuated Control of Inverted Pendulums Zhu, Quanmin, Lei, Changyi, Shi, Baiyang et al. 2025 Journal of the Franklin Institute This work proposes a type of model-free robust underactuated control (MFRUC) framework for improving the efficiency and ...
Why the {{Agent Made Zuo, Rui, Khan, Simon, Wang, Zifan et al. 2025 VisionMask is a standalone explanation model trained end-to-end to identify the most critical regions in the agent's visual input that can explain its actions, hence preserving the agent's performance and integrity.
Towards {{Knowledge-Augmented Agents Alansary, Reem, Ehab, Nourhan 2024 Proceedings of the 16th {{International Conference This position paper argues that the decision-making abilities of such knowledge-augmented solvers transcend those of black-box function approximators alone as the former can generalize through inductive reasoning to behave optimally in unknown states and still remain fully or partially interpretable.
Global {{Lyapunov Alfarano, Alberto, Charton, François, Hayat, Amaury 2024 Advances in Neural Information Processing Systems
{{SymbolicAI Dinu, Marius-Constantin, Leoveanu-Condrei, Claudiu, Holzleitner, Markus et al. 2024 We introduce SymbolicAI, a versatile and modular framework employing a logic-based approach to concept learning and flow...
Meta-{{Learning-Based Adaptive Stability Certificates Jena, Amit, Kalathil, Dileep, Xie, Le 2024 Proceedings of the AAAI Conference on Artificial I This paper addresses the problem of Neural Network (NN) based adaptive stability certification in a dynamical system. Th...
Towards the {{Automatic Synthesis Krishnan, Abhijeet, Martens, Chris 2024 Explainable {{Agency State-of-the-art reinforcement learning agents are capable of outperforming human experts at games like chess, Go, and S...
Explainable {{Reinforcement Learning Milani, Stephanie, Topin, Nicholay, Veloso, Manuela et al. 2024 ACM Comput. Surv. A novel taxonomy for organizing the XRL literature that prioritizes the RL setting is proposed, and three high-level categories are proposed: feature importance, learning process and Markov decision process, and policy-level.
Generative {{Design Pettit, Jacob, Lee, Chak Shing, Yang, Jiachen et al. 2024 Decision trees are an attractive choice for modeling policies in control environments due to their interpretability, con...
Explainable {{Agency 2024 This book focuses on a subtopic of explainable AI (XAI) called explainable agency (EA), which involves producing records...
Combining Data and Theory for Derivable Scientific Discovery with {{AI-Descartes Cornelio, Cristina, Dash, Sanjeeb, Austel, Vernon et al. 2023 Nature Communications A method to enable principled derivations of models of natural phenomena from axiomatic knowledge and experimental data by combining logical reasoning with symbolic regression is developed and demonstrated for Kepler's third law of planetary motion, Einstein's relativistic time-dilation law, and Langmuir's theory of adsorption.
Efficient {{Symbolic Policy Learning Guo, Jiaming, Zhang, Rui, Peng, Shaohui et al. 2023 Deep reinforcement learning (DRL) has led to a wide range of advances in sequential decision-making tasks. However, the ...

🧠 Meta-Learning for Adaptive Control

Meta-learning approaches for fast adaptation in changing control environments.

Title Authors Year Venue TL;DR
A {{Hybrid Meta-Learning Framework Guo, Rui, Li, Yang, Cao, Xiuqing et al. 2026 Verification, {{Model Checking Safety-critical cyber physical systems usually require controllers that not only meet performance goal but also guarante...
{{AI-Driven Control Strategies Lalitha, S D, Danamaraju, Chaitanya, Raj, M. Prabhu et al. 2024 2024 {{Ninth International Conference This research examines power electronics converter AI-driven control techniques in detail and offers new opportunity to construct smart, adaptive, and high-performing energy conversion systems.
Hierarchical {{Meta-learning-based Adaptive Controller Xie, Fengze, Shi, Guanya, O’Connell, Michael et al. 2024 2024 {{IEEE International Conference We study how to design learning-based adaptive controllers that enable fast and accurate online adaptation in changing e...

⚡ Power Electronics (Classical & Data-Driven)

Model-based and data-driven methods for DC-DC converters, inverters, and grid-connected systems.

Title Authors Year Venue TL;DR
(13) {{Power Electronics Meets GenAI 2025
Enhancing {{Power Converters Design 2025
Python and {{SIMETRIX Ansari, Danish Kaleem, Giovanni, Capodivacca, Amin, Syed Usman et al. 2024 2024 39th {{Conference In this paper, an advanced framework for the optimizer of DC-DC buck converters, which utilizes Python for algorithm imp...
Online Switching Control with Stability and Regret Guarantees Li, Yingying, Preiss, James A., Li, Na et al. 2023 Proceedings of {{The This paper considers online switching control with a finite candidate controller pool, an unknown dynamical system, and ...
The Optimal Control of Power Electronic Embedded Networks in {{More Electric Aircraft Dewar, David N. 2021 With the advancement of power electronic technologies over recent decades, there has been an overall increase in the uti...
Model-Based Synthesis of Control for Power Electronic Converters Gilev, Bogdan, Hinov, Nikolay 2021 AIP Conference Proceedings The paper discusses a methodology for model-based synthesis of power electron converter control using the MATLAB/ Simuli...
面向直流供电的电力电子变换器切换面控制及数字化实现 李景灏 2020 近年来,基于电力电子变换器的直流供电技术获得了越来越多的应用,直流供电的电能质量问题也日益凸显。为了满足直流供电系统的电能质量要求,有必要考虑优化电力电子变换器的控制策略以提高系统动态性能。切换面控制是一类非线性控制策略。与传统线性控制相比...
电力电子系统的无源性和抗干扰控制理论与应用研究 贺伟 2018 citation: 13

🔬 AI for Scientific Discovery

AI-driven scientific discovery tools that underpin the next generation of automated engineering.

Title Authors Year Venue TL;DR
An {{AI Aygün, Eser, Belyaeva, Anastasiya, Comanici, Gheorghe et al. 2025 An AI system that creates expert-level scientific software whose goal is to maximize a quality metric is presented, which generated state-of-the-art software for geospatial analysis, neural activity prediction in zebrafish, time series forecasting and numerical solution of integrals.
Towards {{Scientific Discovery Reddy, Chandan K., Shojaee, Parshin 2025 Proceedings of the AAAI Conference on Artificial I Scientific discovery is a complex cognitive process that has driven human knowledge and technological progress for centu...

📦 Other

Title Authors Year Venue TL;DR
Automating {{Automation 2026 Provides society information that may include news, reviews or technical notes that should be of interest to practitione...
Meta-{{Control 2026
Evolutionary Optimization of Model Merging Recipes Akiba, Takuya, Shing, Makoto, Tang, Yujin et al. 2025 Nature Machine Intelligence An evolutionary approach that automatically discovers effective combinations of diverse open-source models, harnessing their collective intelligence without requiring extensive additional training data or compute is proposed, allowing optimization beyond just the weights of the individual models.
Challenges and Opportunities in the Industrial Usage Controller Synthesis Tools: {{A Banerjee, Amar, Choppella, Venkatesh 2025 Results in Control and Optimization Controller synthesis is pivotal in automating control system design from formal specifications and enhancing industrial ...
A Large Language Model for Advanced Power Dispatch Cheng, Yuheng, Zhao, Huan, Zhou, Xiyuan et al. 2025 Scientific Reports A novel dataset construction technique is developed that harnesses various data sources to fine-tune GAIA for optimal performance in power dispatch operations, and streamlines LLM training, allowing for the seamless integration of multidimensional data in power system management.
From {{Mathematical Reasoning Chen, Zhengyu, Wang, Yudong, Xiao, Teng et al. 2025 This study analyzes PRMs from multiple perspectives, including training methodologies, scalability, and generalization capabilities, and indicates that PRMs trained on mathematical datasets exhibit performance comparable to those tailored for code generation, suggesting robust cross-domain generalization.
Leveraging {{Predictions Cui, Wenqi, Xie, Yiheng, Low, Steven et al. 2025 High variability of solar PV and sudden changes in load (e.g., electric vehicles and storage) can lead to large voltage ...
Mathematics with Large Language Models as Provers and Verifiers Duc, Hieu Le, Liberti, Leo 2025 During 2024 and 2025 the discussion about the theorem-proving capabilities of large language models started reporting in...
{{LILAD Jena, Amit, Li, Na, Xie, Le 2025 System identification in control theory aims to approximate dynamical systems from trajectory data. While neural network...
Machine Learning Solutions Looking for {{PDE 2025 Nature Machine Intelligence Machine learning models are promising approaches to tackle partial differential equations, which are foundational descri...
{{AuDeRe Meng, Yue, Chen, Fei, Chen, Yongchao et al. 2025 Recent advancements in large language models (LLMs) have shown significant promise in various domains, especially roboti...
A {{New Embedded Control Architecture 2025
{{OpenAI ChatGPT 2025
Optimization and {{Control 2025
Durvalumab {{With Peters, Solange, Cho, Byoung Chul, Luft, Alexander V. et al. 2025 Journal of Thoracic Oncology Introduction: The primary analysis (median follow-up 34.9 mo across all arms) of the phase 3 POSEIDON study revealed a s...
About {{PSC 2025
{{SVG 2025
Data-Driven Control Methods of Dual-Active-Bridge-Based Grid-Connected Battery Energy Storage System Zeng, Yu 2025 Carbon dioxide emissions cause global warming and a series of environmental problems. To avoid the worst effects of clim...
Decision {{Transformer Zhang, Xiangyuan, Mao, Weichao, Qiu, Haoran et al. 2025 2025 {{American Control Conference Closed-loop control of nonlinear dynamical systems with partial-state observability demands expert knowledge of a divers...
Learning from Models beyond Fine-Tuning Zheng, Hongling, Shen, Li, Tang, Anke et al. 2025 Nature Machine Intelligence A comprehensive review of the current methods based on FM from the perspective of LFM, in order to help readers better understand the current research status and ideas is given.
Data {{Modeling Zuo, Xiangwu 2025 This dissertation investigates approaches in data handling within the domain of Artificial Intelligence (AI), covering d...
{{GENERATIVE AI Chowdhury, Abdullahi, Chowdhury, Adyan, Hoque, Nabila et al. 2024
{{LLM4PLC Fakih, Mohamad, Dharmaji, Rahul, Moghaddas, Yasamin et al. 2024 This work proposes LLM4PLC, a user-guided iterative pipeline leveraging user feed-back and external verification tools - including grammar checkers, compilers and SMV verifiers - to guide the LLM's generation to enhance the generation potential of LLM.
{{AI-driven He, Yang-Hui 2024 Nature Reviews Physics It is argued that while the theorist is in no way in danger of being replaced by AI in the near future, the hybrid of human expertise and AI algorithms will become an integral part of theoretical discovery.
Towards {{General Algorithm Discovery Kuang, Yufei, Wang, Jie, Zhou, Yuyan et al. 2024 Machine learning (ML) approaches have been successfully applied to accelerating exact combinatorial optimization (CO) so...
Online {{Policy Optimization Lin, Yiheng, Preiss, James A., Xie, Fengze et al. 2024 Proceedings of {{Thirty Seventh Conference We study online policy optimization in nonlinear time-varying systems where the true dynamical models are unknown to the...
Meta-{{Control Wei, Tianhao, Ma, Liqian, Chen, Rui et al. 2024 The requirements for real-world manipulation tasks are diverse and often conflicting; some tasks require precise motion ...
Stepwise {{Self-Consistent Mathematical Reasoning Zhao, Zilong, Rong, Yao, Guo, Dongyang et al. 2024 This work introduces a novel algorithm, namely Stepwise Self-Consistent Chain-of-Thought (SSC-CoT), which employs a strategy of selecting intermediate steps based on the intersection of various reasoning chains and enables the model to discover critical intermediate steps by querying a knowledge graph comprising relevant domain knowledge.
Code as {{Policies Liang, Jacky, Huang, Wenlong, Xia, Fei et al. 2023 Large language models (LLMs) trained on code completion have been shown to be capable of synthesizing simple Python prog...
Electrifying {{Discoveries Patero, Judelyn 2023 International Journal of Advanced Research in Scie This research investigates a novel educational paradigm merging interactive technology with conventional pedagogy to enh...
Meta-{{Learning-Based Optimal Control Tang, Zhiqiang, Wang, Peiyi, Xin, Wenci et al. 2023 2023 {{IEEE International Conference Safe and efficient robot-environment interaction is a critical but challenging problem as robots are being increasingly ...
Meta-Control of the Exploration-Exploitation Dilemma Emerges from Probabilistic Inference over a Hierarchy of Time Scales Marković, Dimitrije, Goschke, Thomas, Kiebel, Stefan J. 2021 Cognitive, Affective & Behavioral Neuroscience Cognitive control is typically understood as a set of mechanisms that enable humans to reach goals that require integrat...
电力电子变换器系统先进控制理论及其应用研究 王佐 2020 citation: 3
Policy {{Distillation Rusu, Andrei A., Colmenarejo, Sergio Gomez, Gulcehre, Caglar et al. 2016 Policies for complex visual tasks have been successfully learned with deep reinforcement learning, using an approach cal...
Introduction to {{Physical Modeling Tiller, Michael 2001 3. 8 Problems . . . 66 4 ENABLING REUSE 69 4. 1 Concepts . . . . . . . . 69 4. 2 Exploiting commonality 70 4. 3 Reusable...
Large {{Language Models Dharmaji, Rahul
{{FAST Pertsch, Karl, Stachowicz, Kyle, Ichter, Brian et al. Autoregressive sequence models, such as Transformer-based vision-language action (VLA) policies, can be tremendously eff...

🤝 Contributing

We welcome contributions! Please:

  1. Fork this repo
  2. Add your paper to the relevant section (keep chronological order)
  3. Submit a pull request

Or open an Issue to suggest a paper.


📄 License

MIT © cgcui

About

A curated list of awesome papers, datasets, and resources at the intersection of Large Language Models (LLMs) and Control Systems.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors