FSM
A foundational mathematical model in computer science for describing system behavior, composed of finite states, an initial state, input events and state transition rules. A system can occupy only one definite state at any moment and migrates according to preset rules upon receiving input. In agent design, it converts reasoning processes into enumerable, testable state transition sequences.
Core Facts
Timeline (last 90 days)
A finite state machine (FSM) is a fundamental mathematical model in computer science for describing system behavior, consisting of a finite set of states, an initial state, a set of input events, and transition rules between states, and the system can only be in one definite state at any given moment.
Constrained decoding allows only tokens conforming to grammar rules to be sampled by setting the logits of illegal tokens to negative infinity at each decoding step; FSM is applicable to regular languages, while CFG can handle nested structures such as JSON and XML.
The finite state machine (FSM) approach makes tools invisible to the model directly—preventing it from seeing tools it is not allowed to call—serving as a hard constraint that is more effective than relying on model compliance.
All Facts (7)
Compared to Finite State Machines (FSM), the core advantage of Behavior Trees lies in their modularity and composability.
65%UnverifiedFSM相比直接用if-else堆砌逻辑的优势在于每个状态的行为逻辑完全独立封装，添加新状态不会影响已有状态
90%UnverifiedGodot的节点树天然适合实现有限状态机，每个状态对应一个子节点，父节点负责状态切换逻辑
80%UnverifiedThe Finite State Machine (FSM) is the most classic architectural pattern in game AI design, with the core idea that an object can only be in one of a finite number of states at any given moment.
60%UnverifiedA finite state machine (FSM) is a fundamental mathematical model in computer science for describing system behavior, consisting of a finite set of states, an initial state, a set of input events, and transition rules between states, and the system can only be in one definite state at any given moment.
50%UnverifiedConstrained decoding allows only tokens conforming to grammar rules to be sampled by setting the logits of illegal tokens to negative infinity at each decoding step; FSM is applicable to regular languages, while CFG can handle nested structures such as JSON and XML.
50%UnverifiedThe finite state machine (FSM) approach makes tools invisible to the model directly—preventing it from seeing tools it is not allowed to call—serving as a hard constraint that is more effective than relying on model compliance.
50%