Combining LLMs and Genetic Search for ARC-AGI-2

arXiv:2609.27242 · cs.NE, cs.AI · Submitted 2026-09-23 · Read on arXiv

cs.NE, cs.AI

Submitted: 2026-09-23

Updated: 2026-09-23

Terminology

• Core — 32× in this paper · explained in 2 episodes
• Abstraction — 2× in this paper · explained in 1 episode
• Abstraction and Reasoning Corpus — 2× in this paper
• Benchmark — 2× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Domain-Specific Language (DSL) — 1× in this paper · explained in 2 episodes
• KV cache — 1× in this paper · explained in 3 episodes
• Nadia — 1× in this paper · explained in 2 episodes
• Resource Constraints — 1× in this paper · explained in 3 episodes
• Speculative Decoding — 1× in this paper · explained in 2 episodes
• Thinking mode — 1× in this paper · explained in 2 episodes

Sources

• ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems
• On the Measure of Intelligence
• Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI
• HYSYNTH: Context-Free LLM Approximation for Guiding Program Synthesis
• ConceptSearch: Towards Efficient Program Search Using LLMs for Abstraction and Reasoning Corpus (ARC)
• Procedural Refinement by LLM-driven Algorithmic Debugging for ARC-AGI-2

Related papers

• Evolutionary Ensemble of Agents
• Encoding and Decoding Temporal Signals with Spiking Bandpass Wavelets
• Large Language Models and Evolutionary Computation: A Critical Review of Bidirectional Interaction, Automated Algorithm Design, and Co-Adaptive Systems
• Learning Alzheimer's Disease Signatures by bridging EEG with Spiking Neural Networks and Biophysical Simulations
• Investigating Hyperparameter Optimization and Transferability for ES-HyperNEAT: A TPE Approach
• S-AI-Recursive: A Bio-Inspired and Temporal Sparse AI Architecture for Iterative, Introspective, and Energy-Frugal Reasoning