Compiling Known Rules into Compact Neural Agents: Weight-Space Programming on Unseen Games
cs.AI, cs.LG
Submitted: 2026-11-12
Updated: 2026-11-12
Code: https://github.com/csinva/weight-space-programming-autoresearch
Terminology
Sources
- Can an LLM Actually Reason and Program about Neural Network's Weights or is it just memorization on steroids? Exploring "Weight-Space Programming"
- ARC-AGI-3: A New Challenge for Frontier Agentic Intelligence
- Neural-Symbolic Learning and Reasoning: A Survey and Interpretation
- On the Measure of Intelligence
- ARC Prize 2024: Technical Report
- ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems
- TerpreT: A Probabilistic Programming Language for Program Induction
- Distilling the Knowledge in a Neural Network
- Exploring Weight-Space Programming: Capabilities, Generalization, and Limitations
- Tycho: Active Abstraction with Programmatic World Models for ARC-AGI-3
- Modular Discovery of General Game-Playing Algorithms with Large Language Models
- Weight-space programming for auditing clinical decision networks
- Learning to Learn with Generative Models of Neural Network Checkpoints
- Graph-Based Exploration for ARC-AGI-3 Interactive Reasoning Tasks
- Policy Distillation
- High-Dimensional Continuous Control Using Generalized Advantage Estimation
- Proximal Policy Optimization Algorithms
- Residual Policy Learning
- Neural Network Diffusion
- Position: Weight Space Should Be a First-Class Generative AI Modality
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- 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
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents