Pinned
the coolest point is that now once you build any agentic application with any multiagent framework, you can always use the chain-of-agents paradigm and multiagent distillation to train an end2end agent model that works similarly and can be iteratively optimized with online data
Chain-of-Agents
Interesting idea to train a single model with the capabilities of a multi-agent system.
84.6% reduction in inference cost!
Distillation and Agentic RL are no joke!
Here are my notes:
