Unverified50% confidenceFactExact time
NeoHorse-1-4B improves itself by observing the decision-making process of a real-time routing system, rather than by learning from static samples.
1
Sources
50%
Confidence
Long-term
Relevance
9/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedNeoHorse's self-recursive loop occurs during the training phase and is not triggered during the inference phase.69% similarUnverifiedA true Agentic system has autonomous loop decision-making capability, operating in an observe-think-act cycle where the number of iterations is not predetermined.66% similarUnverified现有持续学习评估指标存在内在张力，系统可通过记住所有旧任务但完全不迁移来刷高某些指标60% similarUnverifiedThe core value of a live runtime lies in building a closed-loop feedback system that shortens the distance between error occurrence and error correction.59% similarUnverified工作流是确定性的、按预设路径执行，而智能体中的大模型会自主决定调用哪些工具、何时停止58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/924335API
curl https://kongchang.com/api/v1/knowledge/claims/924335MCP
get_claim(id=924335)