Metraipolis › archive › dc_c5eb70ec5d2c

Decomposition Buys Integrity, Not Yield — arXiv:2609.17464

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.17464
License (as archived)
CC0-1.0
Archived
2026-10-15T18:31:18.273Z
SHA-256 of the archived text
c2ef765e5ff3451b503751dfdc4f84bf5a38aa92c7f8f768699fc372fc1ecbf0
Stable URL of this page
https://metraipolis.com/documento/dc_c5eb70ec5d2c

How to cite

Decomposition Buys Integrity, Not Yield — arXiv:2609.17464 — arXiv (en), https://arxiv.org/abs/2609.17464 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c5eb70ec5d2c (Metraipolis archive dc_c5eb70ec5d2c, sha256 c2ef765e5ff3451b503751dfdc4f84bf5a38aa92c7f8f768699fc372fc1ecbf0)
BibTeX
@misc{dcc5eb70ec5d2c,
  title = {Decomposition Buys Integrity, Not Yield — arXiv:2609.17464},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.17464},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c5eb70ec5d2c; sha256 c2ef765e5ff3451b503751dfdc4f84bf5a38aa92c7f8f768699fc372fc1ecbf0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.17464. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-16 in cs.MA).
Categorie arXiv: Multiagent Systems (cs.MA) ; Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC).
Pagina del lavoro: https://arxiv.org/abs/2609.17464 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-15T18:00:46.639Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).