Tag
This paper proposes an LLM-driven unified conversion framework that enables automatic and semantically consistent transformation between behavior trees and finite state machines in autonomous intelligent systems, improving scalability and maintainability.
This paper proposes a decoupled data approach to improve turn-taking in full-duplex dialogue by learning from real spoken dialogues while using text for semantics, leveraging a neural finite state machine framework to enhance naturalness and preserve semantic capabilities.
A paper investigates the contribution of agent harnesses versus models to agent behavior, collapsing traces into a compact finite-state machine validated across twelve datasets.