Generative Recursive Reasoning
- Published
- Source
- arXiv
- Paper number
- 190
- Field
- AI / General
- arXiv ID
- 2605.19376
Key points
- Majority voting selects the most common answer among a set of samples.
- Stochasticity shows that the probabilistic nature of latent states is a powerful tool for structured reasoning and overcomes determinism by preventing models from getting stuck in suboptimal deterministic trajectories.
- Width-based scaling introduces a way to expand reasoning performance by increasing the number of parallel samples, or width, instead of simply increasing sequence length or model size.
Paper links
External research summaries. These are not HDATF publications or measured product results.