Decomposition Buys Integrity, Not Yield
Study of 600 production deep-research traces finds agent-tree decomposition loses findings at rate N^(1-δ); flat architectures maximize yield.
The paper models multi-agent decomposition as a tree where an agent holding b items retains each with probability r(b); with r(b)=1/b every tree delivers exactly one finding regardless of shape. Analysis of 600 production deep-research traces estimates delta=0.34 retention decay, and 1,012 annotated traces show one brief in sixteen goes off-target per tier, giving an alignment penalty of 0.536. Depth still cuts root context exposure from N to N^(1/k) and is cheaper at scale, with a hazard model over 743,819 production tool calls showing delegation is an opening move rather than a response to filling context.
- Model predicts flat agent trees maximize yield; retention decays as N^(1-delta)
- Production traces measure delta=0.34 with per-tier alignment penalty 0.536
- One brief in sixteen goes off-target per decomposition tier
- Depth cuts root context exposure from N to N^(1/k) and costs less at scale
- Only 0.7-11.3% of production sessions are worth delegating
From the original article
1 min read at arxiv.orgMulti-agent systems split a task across a tree of agents and justify the split with folklore: smaller contexts, cleaner separation, parallelism. We ask what the split does to how much of what the leaves discover reaches the root. Model a decomposition as a tree in which an agent handed $b$ items keeps any one with probability $r(b)$.
By Rong He · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.