# Carnegie Mellon research shows unified training method for AI models > Source: > Published: 2026-10-30 21:57:39+00:00 # Carnegie Mellon research shows unified training method for AI models Photo: Steve A Johnson / Pexels A new paper argues pretraining, fine-tuning, and reinforcement learning can run as one algorithm instead of three separate stages Most foundation models are built like a three-course meal: pretraining first, fine-tuning second, reinforcement learning for dessert. A new paper from Carnegie Mellon University suggests the courses might work better served on one plate. The study, titled **“Training Foundation Models with a Single Algorithm,”** argues that blending all three types of training data into one unified method can beat the traditional staged approach. ## What the researchers actually did The paper appeared on arXiv on October 29, 2026. Its lead author is Yuda Song of CMU, who worked alongside collaborators from Johns Hopkins University and Aurora Innovation. The core idea is a reframing. The team treats every training stage as maximum-likelihood fitting of model-generated data. That shift moves the important decisions somewhere new. Instead of a rigid sequence of distinct phases, the framework puts the emphasis on data composition and scheduling. Static datasets, the kind used in pretraining and supervised fine-tuning, get folded together with the data management used in reinforcement learning. Everything flows through one training framework. ## The results so far According to the paper, the unified approach improved the tradeoff between accuracy and compute. Translation: the models got more performance out of the same processing budget. ### AI, tech, and the markets they move—in one daily briefing. Daily. Free. Join 34,000+ readers across crypto, finance, and policy. The method also outperformed staged training across several measures. These included in-distribution evaluations, generalization, and readiness for continual learning. The researchers also report that unified training helped models keep broader capabilities across many tasks. The framework removes the need for separate infrastructure built for each training stage, which the authors say simplifies training systems overall. The experiments covered models with around 124 million parameters and around 0.76 billion parameters. ## Why the three-stage recipe exists in the first place The staged pipeline became standard because each phase seemed to do a distinct job. Pretraining builds broad knowledge, fine-tuning teaches the model to follow instructions, and reinforcement learning shapes behavior toward preferred outcomes. The CMU paper challenges that separation directly. It is described as the first public presentation of a unified-training framework backed by supporting experiments. The authors go a step further. They argue such a framework could open new ways to understand how capabilities emerge in models, and how those capabilities are retained as models evolve. ## What this means for AI developers As of October 30, 2026, the research had produced no notable commercial applications or market partnerships. Discussion has stayed mostly inside the academic community, focused on what a single training system could mean for model development. **Disclosure:** This article was edited by Diego Almada Lopez. For more information on how we create and review content, see our [Editorial Policy](https://cryptobriefing.com/editorial-policy/). ## More in Technology [See all](https://cryptobriefing.com/tech/)