Unverified85% confidenceFactTime unknown
现代LLM-based Agent的核心突破发生在2023年前后，随着GPT-4、Claude等大模型具备了稳定的指令跟随和工具调用能力
1
Sources
85%
Confidence
Long-term
Relevance
5/31/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIt was not until GPT-4-level models appeared in 2023 that LLMs had sufficient reasoning capability to drive reliable Agent systems.79% similarUnverifiedSince 2024, with the leap in reasoning capabilities of large models such as Claude and GPT-4o, and the emergence of Agent-based programming tools such as Cursor, Windsurf, and Devin, AI Agent-assisted programming has moved from experimental attempts into production-level application.78% similarVerifiedSince 2023, with the leap in reasoning capabilities of large language models such as GPT-4 and Claude, Agents have rapidly moved from academic concepts to engineering practice.77% similarUnverifiedThe core breakthrough of GPT-5.5 compared to previous generation models lies in the maturation of its Autonomous Agent capability.76% similarUnverified提示词工程（Prompt Engineering）兴起于2022年前后，随着GPT-3、DALL-E等大模型的普及而受到广泛关注75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/5876API
curl https://kongchang.com/api/v1/knowledge/claims/5876MCP
get_claim(id=5876)