跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+86新增论文
+61其中 AI 相关
+14已有论文修订
+93新增 AI 导读

arXiv 最近完成扫描:2026-11-16 01:34 · 全站最近入库:2026-11-16 10:40各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 10:58 — 2026-11-16 10:58(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-16 01:34最近发现新增版本:2026-11-16 10:40库内论文最新更新时间:2026-11-13 16:48

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

23,434 已收录论文19,641 AI 相关6,765 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 1 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33(北京时间)
新论文 · v1arXiv:2611.10620

What Do Collusion Probes Read? Three Pitfalls in Evaluating Multi-Agent Collusion Monitors

Mainul Hasan Mohsin, Mohammad Shahidur Rahman

原文摘要

Activation probes look like near-perfect monitors for secret collusion among large language model (LLM) agents. We show that they mostly detect that an agent was told to collude, not that it decided to. Our benchmark (2,500 committee and 1,476 code-review episodes) adds agents who receive the collusion instruction and refuse it, separating instruction from decision. Published detectors barely tell colluders from these refusers, and our best probe separates them mostly by reading the instruction: without it, agent AUROC falls from 1.00 to 0.61. Two further pitfalls inflate reported results: scored after the vote, a rule that only reads the votes reaches AUROC 0.990 but finds nothing before it; and in 57% of attempts no colluder argues for the target in public. The decision is still there: a probe trained on agents' own choices reads it (AUROC 0.73 without the instruction), and probes find colluders whose goal was fine-tuned into the weights (AUROC 0.995; pre-registered). We turn the controls into a protocol for testing any collusion monitor, and adapt scan statistics into an online monitor for groups of any size.

cs.LG · cs.AI · cs.CL · cs.MA