augmented language model
In plain wordsA language model hooked up to extras — a search engine, a calculator, a memory store or other tools — so it can do things a model working only from its training cannot.
A language modellanguage model, n.: A system that has learned how likely different sequences of words are, so it can predict the next word in a text and, by doing that repeatedly, write text of its own. combined with external components that extend what it can do at inferenceinference, n.: Drawing a conclusion from evidence. In today's AI it most often means running an already-trained model to get an answer, as opposed to training it. time: retrieval of documents or memories, tooltool, n.: Any outside capability an AI model is allowed to use — a web search, a calculator, a code runner, a database or an app — described to the model so it can ask for it by name. calls such as calculators, search engines and code interpreters, and reasoning procedures that break problems into steps. The term places such systems on a continuum between bare language models and full 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.: an augmented model may draw on non-parametric knowledge and act on the world, yet its control flow can still be fixed by the developer. Anthropic's 2024 guide to agents uses 'the augmented LLM' — a model with retrieval, tools and memory — as the basic building block from which workflowsagentic workflow, n.: A multi-step process in which AI models draft, check, use tools and revise their work over several rounds, instead of answering in one shot; often the steps are laid out by developers in advance. and agents are composed.
Any augmented language model with search can answer this; the hard part is citing the sources correctly.
Origin
Popularized by the survey 'Augmented Language Models' (Grégoire Mialon, Roberto Dessì, Maria Lomeli and colleagues at Meta AI, February 2023), which grouped retrieval, tool use and reasoning under one heading. Narrower forms such as 'retrieval-augmented' (2020) and 'tool-augmented' (2022) came earlier.
Related
- tool usetool use, n.: An AI model's ability to reach beyond its own knowledge by operating outside tools — searching the web, running code, using a calculator or an app — and folding the results into its work.
- retrieval-augmented generationretrieval-augmented generation, n.: Giving an AI an open-book exam: before answering, it looks up relevant passages in a set of documents and bases its reply on them, often citing where each point came from.
- 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.
- ToolformerToolformer, prop. n.: A 2023 Meta research model that learned on its own when a tool — a calendar, a translator, a search engine, a calculator — would help it predict text, keeping only the tool uses that actually paid off.
- MRKL systemMRKL system, n.: An early design, pronounced 'miracle', in which a language model acts as a switchboard, sending each part of a question to the right specialist — a calculator, a database, a search tool — and combining the answers.
- agentic workflowagentic workflow, n.: A multi-step process in which AI models draft, check, use tools and revise their work over several rounds, instead of answering in one shot; often the steps are laid out by developers in advance.
Sources
- Mialon, G., Dessì, R., Lomeli, M. et al. (2023). Augmented Language Models: a Survey. arXiv:2302.07842. arxiv.org/abs/2302.07842
- Schluntz, E. & Zhang, B. (2024). Building effective agents. Anthropic. anthropic.com/research/building-effective-agents
Mentioned in
MRKL systemMRKL system, n.: An early design, pronounced 'miracle', in which a language model acts as a switchboard, sending each part of a question to the right specialist — a calculator, a database, a search tool — and combining the answers., program-aided language modelprogram-aided language model, n.: A technique in which an AI solves a math or logic problem by writing a small computer program and letting a computer run it, instead of doing the arithmetic in its head., ToolformerToolformer, prop. n.: A 2023 Meta research model that learned on its own when a tool — a calendar, a translator, a search engine, a calculator — would help it predict text, keeping only the tool uses that actually paid off.