Unverified50% confidenceFactExact time
In the LLM context, an agent usually refers to a system with a large language model as its decision-making core that can cyclically execute "observe-think-act".
1
Sources
50%
Confidence
Long-term
Relevance
10/28/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe decision-making brain of an agent operates based on the reasoning capabilities of large language models (LLMs), with GPT, DeepSeek, and Tongyi belonging to this category.79% similarVerifiedSemantic agents with LLMs at their core understand task intent rather than memorizing operation paths, theoretically enabling a significant improvement in cross-version robustness.76% similarUnverifiedIn an agent, the large model is responsible for reasoning and planning decisions, while tools are responsible for executing tasks, with tool invocation uniformly controlled and decided by the large model.76% similarUnverifiedIn the ideation stage, LLMs can serve as thought stimulators, listing multiple angles of entry or raising counterarguments.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1107151API
curl https://kongchang.com/api/v1/knowledge/claims/1107151MCP
get_claim(id=1107151)