Prior or Feedback? What an LLM Uses When Adapting Neural Operators
cs.AI, cs.LG, physics.comp-ph
Submitted: 2026-10-08
Updated: 2026-10-08
Sources
- Agentic Bayesian Optimization through Surrogate-Augmented Autoresearch
- Can LLMs Beat Classical Hyperparameter Optimization Algorithms? A Study on autoresearch
- Lang-PINN: From Language to Physics-Informed Neural Networks via a Multi-Agent Framework
- Poseidon: Efficient Foundation Models for PDEs
- AgentHPOBench: A Benchmark For Evaluating LLM Agents as Sequential Hyperparameter Optimizers
- Auditing Provenance Sensitivity in LLM Agent Action Selection
- Large Language Models to Enhance Bayesian Optimization
- The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
- Human-in-the-Loop Meta Bayesian Optimization for Fusion Energy and Scientific Applications
- Sequential Large Language Model-Based Hyper-parameter Optimization
- Multiple Physics Pretraining for Physical Surrogate Models
- Walrus: A Cross-Domain Foundation Model for Continuum Dynamics
- Physics-informed fine-tuning of foundation models for partial differential equations
- Prior Knowledge or Search? A Study of LLM Agents in Hardware-Aware Code Optimization
- When Is an LLM Worth It for Hyperparameter Optimization? A Budget-Matched Study on Tabular Data Finds the Warm-Start Is a Default Configuration, Not the Model
- Unsupervised Adaptation of PDE Foundation Models
- Can AI Scientist Agents Learn from Lab-in-the-Loop Feedback? Evidence from Iterative Perturbation Discovery
- OpInf-LLM: Parametric PDE Solving with LLMs via Operator Inference
- How Consistent Are LLM Agents? Measuring Behavioral Reproducibility in Multi-Step Tool-Calling Pipelines
- Using Large Language Models for Hyperparameter Optimization
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems