arXiv 论文提出协调税模型，实测多智能体 LLM 流水线难以胜过单次强模型调用

View PDF HTML (experimental)

Abstract:Multi-agent LLM pipelines built on interoperability protocols such as the Open Floor Protocol (OFP) or A2A are usually justified on capability grounds, with their runtime cost treated as an overhead of unknown size. Comparing such a pipeline with one model call is underspecified, because a pipeline can give each role a different model. We give a closed-form model that sets the coordination tax (decomposition overhead plus per-handoff protocol cost) against the heterogeneity dividend from routing work to a cheaper model, with a break-even threshold and a feasibility bound, $\alpha < 1/r$, and measure every term, with OFP as the protocol under test, on 135 HumanEval and ClassEval tasks in 2430 runs of six architectures with Claude Opus 5.5 and Haiku 5.5. The protocol adds 7.2 ms per handoff, 0.11% of pipeline wall time. Decomposition does not pay on these tasks: a planner-coder-reviewer pipeline costs 3.22x as much as a single strong call, takes 3.24x as long, and solves no more tasks. Moving planner and reviewer to the cheap model cuts the pipeline's cost to 0.39x but changes pass@1 by -6.7 points, leaving it dearer, slower and less accurate than the single call, and the break-even forecast misses by -19% because the cheap roles inflate token volume. The saving lies in choosing a model per task instead: an oracle choice between the two single calls solves 94.3% of runs at half the strong call's cost per solved task.

Submission history

From: Diego Gosmar [view email]
[v1] Sun, 25 Oct 2026 11:41:30 UTC (56 KB)