Meta has released Muse Spark 1.2, a coding-focused update to its previous model, alongside the co-trained Muse Code toolset. The update significantly scales up training compute on coding tasks while expanding training environment diversity.
- Improvements in code generation, complex debugging, and codebase understanding.
- Enhanced end-to-end developer workflows through co-training with Muse Code.
- Extensive training on long-horizon tasks including whole-repository generation and auto-research.
- Integration of rejection sampled harness trajectories and recipe optimizations for goals and subagents.
The release aims to maximize harness compatibility and ensure the model exhibits its best performance and coding usability when paired with the Muse Code toolset.