ALEXANDRIA, Va., Aug. 5 -- United States Patent no. 12,701,054, issued on Aug. 4, was assigned to Cisco Technology Inc. (San Jose, Calif.).

"Teaching LLM-based agents to troubleshoot networks using reinforcement learning" was invented by Gregory Mermoud (Venthone, Switzerland), Pierre-Andre Savalle (Rueil-Malmaison, France), Gregoire Magendie (Lamorlaye, France), Jean-Philippe Vasseur (Combloux, France) and Eduard Schornig (Haarlem, Netherlands).

According to the abstract* released by the U.S. Patent & Trademark Office: "In one implementation, a device uses a large language model-based agent to complete a task with respect to a computer network. The device makes an evaluation of an action taken by the large language model-based agent to c...