Unverified50% confidenceSolutionExact time
In each iteration of the loop, an agent needs to repackage the system prompt, conversation history, tool descriptions, and all outputs from previous steps before feeding them into the model, causing token consumption to grow linearly or even super-linearly with the number of steps.
1
Sources
50%
Confidence
Long-term
Relevance
9/4/2026
First Seen
Sources
Related Entities
Related Claims
Unverified智能体工作负载系统通常基于规划-执行-反馈循环，底层依赖大语言模型的链式推理和工具调用能力77% similarUnverifiedIn multi-turn conversations, before each new response is generated, the system must re-input all prior conversation history into the model, causing token consumption to accumulate and grow with each turn75% similarUnverifiedLarge model output generation uses an autoregressive approach to produce tokens one by one, requiring recalculation of attention over all preceding context with each token generated.73% similarUnverifiedPrompt engineering is evolving from general techniques toward model-specific optimization72% similarUnverifiedThe workflow loop of this methodology is: Plan → Prompt → Generate → Review → Iterate.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/856678API
curl https://kongchang.com/api/v1/knowledge/claims/856678MCP
get_claim(id=856678)