Agents at Scale: Inside MiniMax's Model and the Infrastructure Behind It
- Day
- Day 3 — Session Day 2 · Wed, Jul 1
- Time
- 2:50pm-3:10pm
- Room
- Track 9 · Room 2016
- Track
- Posttraining & Midtraining
Post- and mid-training — what's next after RLHF, decentralized RL training at scale, and the infrastructure behind frontier models.
Accessible with the Engineering pass and above.
About this session
Olive Song (RL Lead, https://www.minimax.io/) and Dan Fu (VP of Kernels, https://www.together.ai/) dig into the engineering behind one of the most widely used open model families in the agent ecosystem: how MiniMax built the model for agentic workloads, and what it takes to serve it at scale.
Olive on the model side:
The RL decisions behind long-context reasoning and tool use
What training for agentic behavior actually looks like in practice
Dan on the infrastructure side:
Why agentic workloads break inference engines built for chat: prefill-heavy traffic, high cache hit rates, long-context inputs
The kernel-level optimizations built for MiniMax's workload profile
How the two teams collaborate on model launches and ongoing performance work
