arXiv cs.MA· Hoang-Loc Cao, Truong Thanh Hung Nguyen, Phuc Truong Loc Nguyen, Vo Thanh Khang Nguyen, Phuc Ho, Hung Nguyen, Duc Pham, Long Tran-Thanh, Hung Cao·· 11 小时前AI 评分24
复制还是佐证？多智能体辩论中证据依赖的公理化框架
Replication or Corroboration? An Axiomatic Framework for Evidential Dependence in Multi-Agent Debate
AI 导读
研究提出一个公理化框架，用于区分多智能体辩论中匹配报告来自复制（同一证据被重复提交）还是佐证（独立证据根源支持同一主张）。作者证明根复制不变性（RRI）等价于阈值一致的复制免疫，并引入 lineage quotient 表示，在 28,224 个直接星型剖面和 2,052 个多层 DAG 上验证了复制与佐证的可分离性。
正文
Abstract:In multi-agent debates, matching reports can arise for two different reasons: agents may repeat the same evidence (replication), or they may provide separate evidential roots that support the same claim (corroboration). A judge must distinguish these two cases. Counting report occurrences gives extra weight to relays, paraphrases, alias resubmissions, and excerpt splits, while merging all matching content avoids this only by also removing genuine corroboration. We formalize this tension as a minimal judgment game in which acquiring new evidence is costly, but replication is cheap. We show that root replication invariance (RRI) is exactly threshold-uniform replication immunity. Under RRI, replication-only deviations cannot change the verdict, and positive-cost replication is strictly dominated, whereas occurrence-sensitive and content-keyed judges admit profitable deviations. We also establish an information boundary: if a judge's observation interface cannot distinguish a replica from a matched fresh root, no judge can both ignore the replica and respond strictly to the fresh root. To preserve this distinction, we introduce the lineage quotient, which removes wording, identity, occurrence multiplicity, and arbitrary root names while keeping distinct roots separate. On orbit-connected domains, it is the coarsest representation sufficient for every deterministic judge invariant to replication and root-label renaming. We further lift this construction to quantitative bipolar argumentation frameworks (QBAFs), characterize strict fresh-root response, prove its propagation along sign-consistent paths under DF-QuAD, and derive a tight closed-form response modulus. Exhaustive audits over 28,224 direct-star profiles, 2,052 multi-layer DAGs, with matched interventions on 277 AVeriTeC-derived profiles, show the predicted separation between replication and corroboration under a supplied partition.
| Subjects: | Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI); Logic in Computer Science (cs.LO) |
| Cite as: | arXiv:2610.36151 [cs.MA] |
| (or arXiv:2610.36151v1 [cs.MA] for this version) | |
| https://doi.org/10.48550/arXiv.2610.36151 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Truong Thanh Hung Nguyen [view email]
[v1]
Mon, 26 Oct 2026 18:53:17 UTC (92 KB)
来源：arXiv cs.MA · arxiv.org