Unmasking shortcut solutions of coding agents on partial differential equations
math.NA, cs.NA
Submitted: 2026-11-09
Updated: 2026-11-09
Code: https://github.com/linghujiale/PDEViBench
Terminology
Sources
- MooseAgent: A LLM Based Multi-agent Framework for Automating Moose Simulation
- A Priori Generalization Analysis of the Deep Ritz Method for Solving High Dimensional Elliptic Equations
- Finite Expression Method for Solving High-Dimensional Partial Differential Equations
- Fourier Neural Operator for Parametric Partial Differential Equations
- PDE-Net: Learning PDEs from Data
- Towards Foundation Models for Scientific Machine Learning: Characterizing Scaling and Transfer Behavior
- PDEformer: Towards a Foundation Model for One-Dimensional Partial Differential Equations
- In-Context Learning of Linear Systems: Generalization Theory and Applications to Operator Learning
- SciML Agents: Write the Solver, Not the Solution
- FEABench: Evaluating Language Models on Multiphysics Reasoning Ability
- FARMS: A Verifiable Foundation for Automated Computational Science
- Iteris: Agentic Research Loops for Computational Mathematics
- Evaluating Large Language Models Trained on Code
- SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
- MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering
- SciCode: A Research Coding Benchmark Curated by Scientists
- ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery
- PDEBENCH: An Extensive Benchmark for Scientific Machine Learning
- PDEAgent-Bench: A Multi-Metric, Multi-Library Benchmark for PDE Solver Generation
- Do Agent Benchmarks Measure Capability? Protocol Validity in the Age of Agentic AI
Related papers
- Do physics-informed neural networks (PINNs) need to be deep? Shallow PINNs using the Levenberg-Marquardt algorithm
- A Neural-preconditioned Poisson Solver for Mixed Dirichlet and Neumann Boundary Conditions
- Advanced Linear Algebra with Applications - Part I (Numerical linear algebra for PDEs, machine learning, and data assimilation)
- Operator learning meets inverse problems: A probabilistic perspective
- Second-order consistency for learning chaotic dynamics via randomized Jacobian matching
- Windowed thinning and query complexity for the bouncy particle and Zigzag samplers