Expired65% confidenceFactExact time
The concept of agents originated from research in reinforcement learning and multi-agent systems.
3
Sources
65%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 9/30/2026(expired)
Sources
OpenAI Codex Deep Dive: The Leap from ChatGPT to an AI Coding Agent
bilibili饭饭大王ouo6/23/2026
Related Claims
VerifiedAgent Skills decompose an agent's capabilities into modular units that, after reinforcement learning training, can be repeatedly invoked and flexibly combined within a scientific research workflow.81% similarUnverifiedThe core of a custom Agent is a carefully designed System Prompt.80% similarVerifiedAgent Skills adopts a vertical capability scaling approach within a single agent, which is more lightweight and easier to debug than Multi-Agent approaches.79% similarVerifiedThe Agent + Skill combination is a "brain + arms" architecture: the Agent is responsible for understanding intent and formulating plans, while the Skill is responsible for concrete execution.79% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/41533API
curl https://kongchang.com/api/v1/knowledge/claims/41533MCP
get_claim(id=41533)