belief–desire–intention model
In plain wordsA way of designing software agents around three human-like ideas: what the agent believes about the world, what it wants, and which plans it has committed to carrying out.
A model of rational agency, and a family of agent architectures and programming languages built on it, in which an agent's state comprises beliefs (its information about the world), desires (states it would like to bring about) and intentions (desires it has committed to pursuing, usually through partially specified plans). The defining feature is commitment: intentions persist and constrain further deliberation until they are achieved, judged impossible or no longer wanted, which lets agents with limited computing resources act in real time instead of replanning from scratch. In implemented systems, plans are chosen from a library of hand-written recipes triggered by events and goals, a cycle resembling hierarchical task networkhierarchical task network, n.: A planning method that breaks a big task, such as 'travel to Paris', into smaller tasks, such as 'book a flight' and 'pack', using stored recipes, until only simple actions remain. decomposition. Platforms include the Procedural Reasoning System, AgentSpeak with its interpreter Jason, and JACK, used in air-traffic management, defense simulation and spacecraft fault handling. BDI vocabulary is often borrowed to describe language-modellarge language model, n.: A computer program trained on enormous amounts of text to predict the words that come next. At vast scale, that simple skill lets it chat, answer questions, translate, summarize and write code. agentsAI agent, n.: An AI system that does not just answer but acts: given a goal, it decides on steps, uses tools such as a browser or code editor, checks the results and keeps going until the job is done., though without its formal commitment semantics.
Origin
Based on the philosopher Michael Bratman's theory of intention and practical reasoning (Intention, Plans, and Practical Reason, 1987). Michael Georgeff and Amy Lansky's Procedural Reasoning System (1987) implemented the idea, and Anand Rao and Georgeff formalized BDI logics in 1991 and described 'BDI agents' in 1995.
Related
- AI agentAI agent, n.: An AI system that does not just answer but acts: given a goal, it decides on steps, uses tools such as a browser or code editor, checks the results and keeps going until the job is done.
- multi-agent systemmulti-agent system, n.: A setup in which several AI agents, each with its own role or point of view, work together — or compete — on a problem, passing messages and results among themselves.
- hierarchical task networkhierarchical task network, n.: A planning method that breaks a big task, such as 'travel to Paris', into smaller tasks, such as 'book a flight' and 'pack', using stored recipes, until only simple actions remain.
- automated planningautomated planning, n.: The branch of AI that works out a sequence of actions to reach a goal, such as the steps a robot must take to assemble a part, from descriptions of what each action needs and what it changes.
- intentional stanceintentional stance, n.: Predicting what something will do by treating it as if it had beliefs and goals — as we do with people, and often with chess programs and chatbots — whatever is really going on inside.
- cognitive architecturecognitive architecture, n.: A blueprint for a complete thinking system — how memory, attention, learning and decision-making fit together — used both to build general AI agents and to model how the human mind works.
Sources
- Bratman, M. E. (1987). Intention, Plans, and Practical Reason. Harvard University Press.
- Rao, A. S. & Georgeff, M. P. (1995). BDI Agents: From Theory to Practice. Proceedings of the First International Conference on Multi-Agent Systems (ICMAS-95), 312–319.