Unverified50% confidenceFactExact time
Lillian Wang proposed a framework: the language model is the agent's "brain," surrounded by three supporting components: planning, memory and tool use.
1
Sources
50%
Confidence
Long-term
Relevance
11/1/2026
First Seen
Sources
What Really Counts as a True AI Agent? Three Core Elements and One Test
youtubeAI Shadow10/31/2026
Related Entities
Related Claims
VerifiedThe Chain-of-Thought prompting technique was formally proposed by the Google Brain team in the 2022 paper "Chain-of-Thought Prompting Elicits Reasoning in Large Language Models".68% similarVerifiedThe tool-calling mechanism allows large language models to dynamically invoke external functions during inference, representing a fundamental leap from language models to action models.67% similarUnverifiedIn language model-driven war games, the model's language output simultaneously determines what an agent attempts to do and what becomes the simulated reality.67% similarUnverified即梦AI Agent模式的技术依赖于大语言模型（LLM）的推理能力与多模态生成模型的协同配合65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1122454API
curl https://kongchang.com/api/v1/knowledge/claims/1122454MCP
get_claim(id=1122454)