arXiv cs.CY· Jicheng Zhou, Kemou Li, Kahim Wong, Zheyuan Li, Zhuan Shi, Fengpeng Li, Haiwei Wu, Jiantao Zhou·· 2 天前AI 评分32
CABAL：用多智能体模拟追踪同行评审中串通投标的影响
CABAL: Multi-Agent Simulacra for Tracing the Effects of Collusive Bidding in Peer Review
AI 导读
研究者提出 CABAL 多智能体模拟框架，在固定会议环境下用 LLM 驱动的评审智能体分别执行诚实或串通策略，研究评审分配诚信问题。实验显示串通投标使目标论文被捕获率提升一倍以上，被分配的串通者给目标论文打分比诚实共同评审者高约两分，而会议整体影响相对有限。现有投标阶段检测器仅提供有限的串通证据。
正文 · 原文
Abstract:Recent reports during the AAAI-27 review cycle highlight the risk of reviewers coordinating bids for reciprocal assignment advantage. Prior work treats bidding, reviewer assignment, and review manipulation as separate stages, leaving the lifecycle effects of collusive bidding unclear. Real-world analysis is further constrained by typically unobservable collusive intent and the lack of counterfactuals for the same conference. Motivated by this gap, we introduce \alg, an end-to-end multi-agent simulacra framework for studying reviewer assignment integrity by holding the conference environment fixed and configuring LLM-driven reviewer agents with honest or collusive policies. We further develop an affinity-guided collusive bidding strategy that uses mutual reviewer-paper affinities to construct collusion rings and select target papers, producing expertise-consistent rather than arbitrarily targeted attacks. Controlled experiments show that collusive bidding more than doubles target-paper capture and that assigned colluders score target papers about two points higher than honest co-reviewers, while conference-wide effects remain comparatively modest. Evaluated bid-phase detectors provide only limited evidence of collusion: in a fixed-triplet detector stress test, native positive-bid graphs are confounded by benign affinity, while a Very-High-only diagnostic view enables precise but low-coverage local recovery.
| Subjects: | Artificial Intelligence (cs.AI); Computers and Society (cs.CY) |
| Cite as: | arXiv:2609.05227 [cs.AI] |
| (or arXiv:2609.05227v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2609.05227 arXiv-issued DOI via DataCite |
Submission history
From: Jicheng Zhou [view email]
[v1]
Fri, 4 Sep 2026 14:55:33 UTC (1,021 KB)
[v2]
Thu, 15 Oct 2026 08:31:08 UTC (1,021 KB)
来源：arXiv cs.CY · arxiv.org