Unverified60% confidenceFactExact time
In Agent scenarios, each tool call requires the full context to be re-input into the model, causing token consumption to grow exponentially.
2
Sources
60%
Confidence
Long-term
Relevance
7/23/2026
First Seen
Sources
Related Claims
VerifiedIn agentic scenarios, an Agent often initiates multiple rounds of model calls within a single user request, with each round carrying an increasingly longer context, causing costs to grow nonlinearly with conversation depth.77% similarUnverifiedAgent-type tasks use the ReAct think-act-observe loop, and a single user task may trigger dozens or even hundreds of model calls, causing computational overhead to grow non-linearly.77% similarUnverifiedAgents repeatedly execute the perception-planning-action loop in cycles, and each round requires packing the complete history into the context window, causing input tokens to grow linearly or even exponentially.77% similarVerifiedEach Agent run incurs actual API call costs, and as the scale of evaluation use cases grows and retries accumulate, costs can mount rapidly.76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/601702API
curl https://kongchang.com/api/v1/knowledge/claims/601702MCP
get_claim(id=601702)