Huanyu Qu

psRL can boost training throughput by over 5x by efficiently sharing prefixes among samples, addressing a critical bottleneck in agentic AI training.

LLMs can now compress their KV cache more effectively by dynamically synthesizing soft tokens tailored to the input, preserving crucial context that's otherwise lost with static methods.

Scaling LLM-based multi-agent systems doesn't just need better prompts or models, but a whole new software engineering approach focused on managing runtime entropy.