"Agentic AI involves using a large language model (LLM) to carry out multi-step tasks, by connecting it to external tools such as Internet browsers or coding suites. The hope is that AI assistants can be created that simplify real-world tasks. In science, some think that AI agents - perhaps even several working together - will not just save time, but also eventually run their own experiments and generate knowledge."
"But this dream is not yet a reality. Although access to AI agents is already being sold by technology firms, many such agents are either limited in scope or exist in beta versions that require significant human oversight. Because they are based on LLMs, which are, at heart, statistical prediction machines, they are prone to making mistakes known as hallucinations."
"Rather than follow prescribed instructions for each task, agents use LLMs to make and refine plans on the fly for a variety of multi-step goals. Unlike lone LLMs, they also harness tools to take actions in the real world - for instance, to write and run code or navigate databases - with some interacting with each other and using working memory to remember user preferences and previous actions."
Agentic AI uses large language models connected to external tools such as browsers and coding suites to plan and execute multi-step tasks. These agents can write and run code, navigate databases, remember user preferences and coordinate with other agents using working memory. Proponents expect agents to simplify real-world tasks and potentially run experiments and generate scientific knowledge. Many commercially available agents remain limited or in beta and require significant human oversight. Because LLMs operate by statistical prediction, agents can hallucinate and make factual or operational errors, posing risks that demand careful evaluation and mitigation strategies.
Read at Nature
Unable to calculate read time
Collection
[
|
...
]