Inference-Time Scaling and Collective Intelligence for Frontier AI
Sakana AI
Sakana AI developed AB-MCTS, an inference-time scaling algorithm that enables multiple frontier AI models to cooperate and perform trial-and-error reasoning. A combination of o4-mini, Gemini-2.5-Pro, and DeepSeek-R1-0528 using Multi-LLM AB-MCTS achieved significantly higher performance on the ARC-AGI-2 benchmark compared to any individual model. This approach leverages the diverse strengths and weaknesses of different models to solve problems that would be insurmountable for any single model.
Related stories
Together AI at ICML 2026: frontier research across the full stack
Together AI · 2 months ago ·
43
Towards Automating Long-Horizon Algorithm Engineering for Hard Optimization Problems
Sakana AI ·
9
How Together AI Uses AI Agents to Automate Complex Engineering Tasks: Lessons from Developing Efficient LLM Inference Systems
Together AI · 1 year ago ·
6
Towards Automating Long-Horizon Algorithm Engineering for Hard Optimization Problems
Sakana AI ·
9
How Together AI Uses AI Agents to Automate Complex Engineering Tasks: Lessons from Developing Efficient LLM Inference Systems
Together AI · 1 year ago ·
6