Yandex turns the KV cache into a live agent control layer
Most LLM agents still stop, call a tool, append the result, and start again. Yandex argues the bottleneck is not necessarily model training but how inference state is scheduled: shared KV-cache branches could let perception, reasoning, tool use, and action progress concurrently, while revising a trajectory without recomputing everything. The proposal points toward more responsive agents for robots, games, and live software, without changing model weights.