跳到正文
arXiv cs.AI· Ruiqi Liu, Jinming Li, Mo Wang, Yang Lu, Yanlan Kang·· 10 小时前AI 评分22

预算配对反事实审计:为视觉智能体评估选择观察对象

Choosing What to Observe: Budget-Paired Counterfactual Audits for Credible Evaluation of Visual Agents

AI 导读

研究者提出“预算配对反事实审计”评估协议,在固定公开证据与区域绑定的前提下,仅扰动剩余观察预算或声明的任务参数,并为每段已获取的观察历史赋予精确的延续价值。该方法将损失的期望准确率分解为逐步获取损失与终局决策损失,从而把规划能力与固定角色启发式区分开。在四十个配对路由锚点上进行了验证。

正文 · 原文

View PDF HTML (experimental)

Abstract:Visual agents that read dense documents must ration a finite observation budget across candidate regions, yet answer accuracy conflates where an agent looks, how it adapts to the reads that remain, and how it an?swers once observation stops. We introduce budget-paired counterfactual audits, an evaluation protocol that holds public evidence and region bindings fixed while perturbing only the remaining budget or de?clared task parameters, and credits every acquired history with exact continuation values. The resulting accounting decomposes lost expected accuracy into stepwise acquisition loss and terminal decision loss, separating planning from fixed-role heuristics. Across forty paired routing anchors, five open-weight
Subjects: Artificial Intelligence (cs.AI)
Cite as: arXiv:2611.24867 [cs.AI]
  (or arXiv:2611.24867v1 [cs.AI] for this version)
  https://doi.org/10.48550/arXiv.2611.24867

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Ruiqi Liu [view email]
[v1] Wed, 18 Nov 2026 18:20:12 UTC (1,575 KB)

来源:arXiv cs.AI · arxiv.org