ECE285 Agentic AI and LLMs for Smart Grids

Instructors

• Prof. Yuanyuan Shi

  • Email: yyshi@ucsd.edu

  • Office Hour: Monday 2-3pm, FAH 3009

• Daniela Rojas

  • Email: d2rojas@ucsd.edu 

  • Office Hour: Wednesday 5-6pm, FAH2009

Teaching Assistant

Rich Pai, cpai@ucsd.edu

Office Hour: Thursday 1-2pm, FAH2009

Class Time and Location: MW 3:30pm-4:50pm, EBU1 Room#2315

Power System Topics

• Basics of Power Systems

• Demand Response and Load Flexibility

• Renewable Power and Integration

• Economic Dispatch and Unit Commitment

• Power Flows

• Introduction to Electricity Markets

• Introduction to Power System Control

Textbook: Power Systems: Fundamental Concepts and the Transition to Sustainability, Daniel Kirschen

Agentic AI and LLM Topics

• LLM Fundamentals – Transformers & Tokens

Vaswani, A. et al. (2017). Attention Is All You Need. NeurIPS 30. https://arxiv.org/abs/1706.03762

Devlin, J. et al. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. NAACL. https://arxiv.org/abs/1810.04805

Kudo, T. & Richardson, J. (2018). SentencePiece: A Simple and Language-Independent Sub-word Tokenizer. EMNLP-Demo https://arxiv.org/abs/1808.06226

Holtzman, A. et al. (2019). The Curious Case of Neural Text Degeneration. ICLR. https://arxiv.org/abs/1904.09751

• LLM Fundamentals II – Scaling Laws & Pre-training

Brown, T. et al. (2020). Language Models Are Few-Shot Learners (GPT-3). NeurIPS 33. https://arxiv.org/abs/2005.14165

Kaplan, J. et al. (2020). Scaling Laws for Neural Language Models. https://arxiv.org/abs/2001.08361

Raffel, C. et al. (2020). Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer (T5). JMLR 21 https://arxiv.org/abs/1910.10683

• Prompt Engineering, Embeddings & Retrieval-Augmented Generation (RAG)

Wei, J. et al. (2022). Chain-of-Thought Prompting Elicits Reasoning in LLMs. NeurIPS 35. https://arxiv.org/abs/2201.11903

Wang, X. et al. (2022). Self-Consistency Improves Chain-of-Thought Reasoning. NeurIPS 35. https://arxiv.org/abs/2203.11171

Lewis, P. et al. (2020). Retrieval-Augmented Generation for Knowledge-Intensive NLP. NeurIPS 33. https://arxiv.org/abs/2005.11401

• Fine-tuning 

Hu, E. et al. (2021). LoRA: Low-Rank Adaptation of Large Language Models. ICML 38 (Δ). https://arxiv.org/abs/2106.09685

Ding, N. et al. (2024). Parameter-Efficient Fine-Tuning: A Survey. IEEE TPAMI early access https://arxiv.org/abs/2403.14608

• Alignment & RL

Ouyang, L. et al. (2022). Training Language Models to Follow Instructions with Human Feedback (InstructGPT). NeurIPS 35. https://arxiv.org/abs/2203.02155

Rafailov, R. et al. (2023). Direct Preference Optimization: Your LM Is Secretly a Reward Model. ICLR 2024. https://arxiv.org/abs/2305.18290

• Agents I — Planning, Tool Use & API Calling

Yao, S. et al. (2022). ReAct: Synergizing Reasoning and Acting in LLMs. NeurIPS Workshop. https://arxiv.org/abs/2210.03629

Schick, T. et al. (2023). Toolformer: Language Models Can Teach Themselves to Use Tools. EMNLP Findings. https://arxiv.org/abs/2302.04761

Erdoğan, Y. et al. (2025). Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks. ICML 2025 https://arxiv.org/abs/2503.09572

• Agents II — Memory, Reflection & Evaluation

Shinn, N. et al. (2023). Reflexion: Language Agents with Verbal Reinforcement Learning. NeurIPS 2023 Workshop. https://arxiv.org/abs/2303.11366

Park, J. S. et al. (2023). Generative Agents: Interactive Simulacra of Human Behavior. ACM Transactions on Human–Computer Interaction (CHI ’24 journal version) https://arxiv.org/abs/2304.03442