Unverified50% confidenceFactExact time
When the LLM repeatedly calls the same tool but never obtains a satisfactory result, it may fall into an infinite loop.
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Deconstructing ReAct: A Hands-On Guide to Building AI Agents from Scratch
bilibili枫叶边城10/16/2026
Related Entities
Related Claims
Unverified终止条件设计不当会导致无限循环（反复调用工具无法收敛）或过早终止（信息不足时就回复）两类故障73% similarUnverifiedLLM call chains are long and highly non-deterministic, and a single failure may originate from any one of the following: prompt, tool call, context truncation, or model hallucination.72% similarUnverifiedEarly LLMs were prone to stalling on long-horizon tasks, falling into repetition, losing direction, or being unable to recover from errors.72% similarUnverifiedOverly persistent constraints not only cause infinite loops but also deprive the agent of the ability to adjust its strategy based on intermediate results, leaving it unable to escape when it encounters an abnormal return, a tool error, or a need to clarify with the user.71% similarUnverifiedLong-running LLM agent tasks are subject to failure risks such as network interruptions, model rate limiting, and timeouts; the lack of a resumability mechanism causes workflows to need to be rerun from the beginning.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1042398API
curl https://kongchang.com/api/v1/knowledge/claims/1042398MCP
get_claim(id=1042398)