Abstract:Multi-agent LLM systems fail in production at rates between 41% and 87%, mostly due to coordination defects rather than base-model capability. Existing responses split between cataloguing failure modes empirically and shipping declarative orchestration frameworks as engineering tools; neither delivers a principled mapping from coordination configuration to predictable failure-mode signature. We argue that coordination should be treated as a configurable architectural layer, separable from agent logic and from information access, enabling architectural reasoning rather than only engineering productivity.
We instantiate this with an information-controlled design on prediction markets: a single LLM, fixed tools, fixed per-call output cap, and fixed prompt template across five reference coordination configurations, with total compute per question treated as an endogenous architectural output. The Murphy decomposition of the Brier score separates calibration from discriminative power, so configurations leave distinguishable signatures even when aggregate scores coincide.
On 100 Polymarket binary markets resolved after the model's training cutoff (claude-opus-4-6) we report Murphy signatures, a cost-quality Pareto frontier, category-conditioned analysis, and a bootstrap power-projection. Three of five pre-specified predictions are upheld in direction; two configurations dominate the Pareto frontier within this regime; exploratory bootstrap intervals separate consensus alignment from others, though pairwise tests do not survive Bonferroni correction at n=100. We also deploy the same configurations as live agents on Foresight Arena under web-search-enabled conditions, as an on-chain replication channel accumulating in parallel. Harness, trace dataset, and production agents are released. We position this as a methodology-validating first instantiation, not a general cross-model claim.
| Comments: | 31 pages, 7 figures, 4 tables. Code, traces, and production agents publicly released; see Appendix B for repository pinning |
| Subjects: | Multiagent Systems (cs.MA); Machine Learning (cs.LG); Trading and Market Microstructure (q-fin.TR) |
| MSC classes: | 68T42, 62P20, 62F40 |
| ACM classes: | I.2.11; I.2.7; G.3 |
| Cite as: | arXiv:2605.03310 [cs.MA] |
| (or arXiv:2605.03310v1 [cs.MA] for this version) | |
| https://doi.org/10.48550/arXiv.2605.03310 arXiv-issued DOI via DataCite (pending registration) |
From: Maksym Nechepurenko [view email]
[v1]
Tue, 5 May 2026 02:56:44 UTC (412 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。