arXiv cs.AI· Miaobo Hu, Shuhao Hu, Xiaobo Guo, Xin Wang, Bokun Wang, Peng Zhang, Daren Zha·· 12 小时前AI 评分31
ActiveEvidence：面向决策的可验证证据图与采集缺口
ActiveEvidence: Decision-Focused Evidence Graphs with Verifiable Acquisition Gaps
AI 导读
ActiveEvidence 提出反事实证据交互图（CEIG），在免费元数据/付费观测边界下实现可决策认证的主动证据采集，通过缺口导向细化只评估可能改变行动的交互项，并以 ε-决策证书在容差内停止。
正文 · 原文
Abstract:A multimodal agent must decide whether visual evidence is worth acquiring, which candidate or resolution to query, and when further interaction can no longer change its decision. We study this problem under a strict free-metadata/paid-observation boundary, stochastic vector costs, and a frozen execution trace, and treat it as decision-certifiable active evidence acquisition. A Counterfactual Evidence Interaction Graph (CEIG) represents unary evidence value, signed second-order interaction, and directed conditional harm while maintaining explicit score enclosures for unresolved interactions; a decision-weighted enclosure objective tightens the bounds that can change action identity. Gap-directed refinement evaluates only interactions that can displace the incumbent acquisition and stops once an $\epsilon$-decision certificate shows that unresolved terms cannot change the selected action beyond a declared tolerance. The certificate is model-relative: it verifies policy-consistent optimality under the pinned learned score, and semantic quality is measured separately through post-freeze labels. Paired continuation rollouts learn the downstream value of paid previews, an online operational cost filter is separated from independent finite-policy-family trajectory certification, and an acquisition monitor with an independently implemented verifier binds every certificate to the frozen trace. On 640 cases split into 384/128/128 training, validation, and test cases, the controller reaches task score 0.842, grounding F1 0.816, evidence recall 0.873, 1.74 accepted calls, 286.5K visual tokens, and 742ms p95 latency. Dense replay of issued certificates shows 0.992 action agreement and a 0.988 certificate rate while evaluating 19.6 instead of 191.4 expensive interaction terms per decision.
| Comments: | 19 pages, 8 figures |
| Subjects: | Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.20532 [cs.AI] |
| (or arXiv:2610.20532v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.20532 arXiv-issued DOI via DataCite |
Submission history
From: Miaobo Hu [view email]
[v1]
Wed, 14 Oct 2026 17:29:06 UTC (329 KB)
[v2]
Fri, 16 Oct 2026 10:18:07 UTC (329 KB)
来源：arXiv cs.AI · arxiv.org