Recursive Improvement of a Differentiable Scientific Software Ecosystem
cs.AI, physics.comp-ph
Submitted: 2026-10-03
Updated: 2026-10-12
Code: https://github.com/jax-ml/jax
Sources
- The Elements of Differentiable Programming
- AInsteinBench: Benchmarking Coding Agents on Scientific Repositories
- ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments
- Large Knowledge Model: A Knowledge Foundation for Agentic Science at Scale
- Don't Unroll Adjoint: Differentiating SSA-Form Programs
- Systematic LLM Translation of Legacy Scientific Code to Differentiable Frameworks: Application to a Land Surface Model
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
- Universal Differential Equations for Scientific Machine Learning
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