Olive Song leads reinforcement-learning research at MiniMax, overseeing the final training and release of open-weight models for coding and autonomous digital work. She focuses on making agents dependable when tools fail, environments change, tasks run for hours, and imperfect rewards invite shortcuts.
An alumna of New York University’s Courant Institute, Song lived in New York for six years before moving from academic research into industrial model development. In 2025, she helped introduce MiniMax-M2, an open-weight coding model with 10 billion active parameters. By 2026, she was leading reinforcement-learning research for MiniMax’s increasingly multimodal models, including MiniMax-M3.
- Developer-centered reinforcement learning: Song incorporates experienced developers into task design, evaluation, and reward development. Their feedback grounds training in realistic debugging, repository refactoring, multilingual programming, and standards of work that software teams can actually trust.
- Interleaved reasoning and tool use: Her agents alternate actions with reassessment, adapting when tool calls fail or unexpected results emerge. For extended assignments, including research reproduction and GPU-kernel optimization, she evaluates intermediate attempts and uses validation splits to distinguish genuine progress from reward hacking.
- Robustness across agent environments: Song varies prompts, tool definitions, response formats, and surrounding agent scaffolds because familiarity with numerous tools does not guarantee reliable performance inside an unfamiliar production setup.
- Open-weight multimodal models: With MiniMax-M3, she describes training text and visual information together from the outset, enabling agents to interpret interfaces, improve websites, navigate computers, and assist with game development. Open weights also let developers adapt models, protect sensitive data, and contribute improvements.
Song approaches alignment as an implementation problem as much as a theoretical one: one training investigation traced stalled reinforcement-learning progress to numerical precision in the language-model head. Her interests extend into GPU data layouts and shared-memory bank conflicts. She has also outlined her engineering philosophy: identify the real problem, reduce it to essentials, understand its mechanism, validate the solution, and iterate quickly.
