Decomposition Buys Integrity, Not Yield

Abstract:Multi-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 $r(b)$. If $r(b)=1/b$, every tree delivers exactly one finding, for every task size and every shape; we verify this to $2.4 \times 10^{-15}$ on 20,000 random irregular trees. If $r(b)=Cb^{-\delta}$, a depth-$k$ tree over $N$ findings yields $C^k N^{1-\delta}$: task size and architecture separate, and architecture contributes only $C \le 1$ per level, so flat is optimal for yield and no arrangement of agents escapes the exponent $\delta$. On 600 production deep-research traces $\delta = 0.34$ [0.30, 0.38], by three identifications that do not share a failure mode. At a hop where item boundaries come from the tool rather than a text heuristic, and where $b=1$ occurs 550 times, $C = 0.571$ [0.527, 0.615] is observed rather than extrapolated, over 16,082 hops. A tier also costs alignment: on 1,012 annotated multi-agent traces one brief in sixteen goes off-target, giving $\mu = 0.939$ and a per-tier penalty $C\mu = 0.536$. Depth is bought on two other axes. The root context is the only state that persists and the only one that cannot cheaply forget, and depth cuts its exposure from $N$ items to $N^{1/k}$. Depth is also cheaper: production flat agents bill as $N^{1.39}$, not the $N^2$ an append-only context predicts, and at equal spend two tiers overtake flat at 403 findings. Across every parameter we measured the model says 0.7% to 11.3% of production sessions are worth delegating, against 7.8% that do. A hazard model on 743,819 production tool calls finds that delegation does not respond to a filling context and is instead an opening move.

Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC)

arXiv:2609.17464 [cs.MA]

(or arXiv:2609.17464v1 [cs.MA] for this version)

https://doi.org/10.48550/arXiv.2609.17464 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

code/briefing.py

code/diagnose.py

code/estimate.py

code/explore2.py

code/explore_search.py

code/make_arxiv.py

code/measure_C.py

code/measure_C2.py

code/measure_C3.py

code/measure_C4.py

code/measure_C5.py

code/measure_rb.py

code/oneoff/README.md

code/oneoff/add_mu.py

code/oneoff/fix_drift.py

code/oneoff/fix_leads.py

code/oneoff/polish_figs.py

code/oneoff/renumber.py

code/production.py

code/revealed.py

code/verify_pdf.py

code/verify_refs.py

(30 additional files not shown) You must enabled JavaScript to view entire file list.

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.