Download
poetiq-arc-agi-solver is the open-source codebase from Poetiq that replicates their record-breaking submission to the challenging benchmark suite ARC-AGI (both ARC-AGI-1 and ARC-AGI-2). The project demonstrates a system that orchestrates large language models (LLMs) — like those from major providers — with carefully engineered prompting, reasoning workflows, and dynamic strategies, to tackle the abstract, logic-heavy problems in ARC-AGI. Instead of relying on a single prompt or fixed strategy, their solver dynamically adapts the reasoning path, selecting what to ask or analyze next depending on intermediate results — effectively compositing reasoning, perception, and program synthesis (or symbolic manipulation) in a loop. The repository allows others to reproduce their results, experiment with different LLM backends (e.g. the user may supply keys for supported models), and observe how their adaptive meta-system handles the logic and abstraction challenges.
Features
- Reproduces Poetiq’s state-of-the-art solver for ARC-AGI-1 and ARC-AGI-2 benchmarks
- Uses dynamic, adaptive reasoning pipelines (not fixed prompt → respond) to iteratively solve abstract reasoning tasks
- Supports multiple LLM backends (user-supplied API keys), making it flexible and extensible
- Open-source code — enables researchers to inspect, tweak, and extend the reasoning and orchestration logic
- Designed for complex abstraction, logic, and perception problems — not simple NLP tasks
- Serves as a research and experimentation platform for meta-reasoning, few-shot learning, and programmatic problem solving
Project Samples
