Cost dashboards show one multi-agent workflow consuming extreme token volume because the orchestrator and a critic agent refine the same paragraph for dozens of rounds with no stop condition, each round including full history and multiple tool calls. Which optimization strategy best targets this failure mode?
Select an answer to reveal the explanation.
Short Explanation
Unbounded agent loops are a classic token burn. Cap iterations, set per-run token budgets, and stop thrashing the same tools. Adding more critics multiplies cost. Turning text into images does not help LLM token accounting and is the wrong medium. Removing stop conditions makes it worse. A is the token optimization strategy.
Full Explanation
Correct answer: A. Strategies for optimizing token usage include token limits, loop controls, and tool-call constraints. Multi-agent refinement without termination criteria or budgets creates runaway cost and latency.
B is incorrect because adding agents to an unbounded loop increases, not reduces, aggregate token consumption.
C is incorrect because image-encoded history is not a valid general substitute for text token control in agent reasoning pipelines.
D is incorrect because removing stop conditions is the root cause pattern, not a fix.
Exam focus: loop controls and token budgets are first-class multi-agent cost/reliability controls.