---
title: "面向策略感知自主Agent的可解释性框架"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2607.21209v1"
permalink: "https://feed.astralor.com/items/itm_239aca1b136af24dc4e17348"
published: "2026-07-23T11:22:25.000Z"
score: 70
channel: "tech"
tags: ["可解释人工智能","回答集编程","对比解释","自主Agent"]
---

# 面向策略感知自主Agent的可解释性框架

## AI 点评

> 这篇论文最值得关注的是它把社会科学解释理论迁移到AI Agent领域，并用ASP语言优雅地实现了反事实推理。对于那些在研究自动驾驶、服务机器人等需要安全合规决策的开发者来说，这个框架提供了一条可落地的可解释性路径。即使你不做ASP，其核心的对比解释思路也值得借鉴。

## 速览

该论文提出一种面向策略感知自主Agent的可解释性框架，结合社会科学解释理论，利用回答集编程（ASP）与Python实现。框架通过检测违反策略时的罚分来识别反事实事件，生成对比性解释（例如“Agent执行此动作是因为否则会发生不良事件X”）。通过人类调查评估，验证了生成解释的可理解性。

## 关键点

- 提出面向策略约束Agent的可解释性框架，结合社会科学解释理论
- 利用反事实思维生成对比解释，通过罚分信号定位不良事件
- 使用ASP语言建模，Python辅助信息抽取与自然语言翻译
- 通过人类调查评估解释质量，验证框架有效性

## 全文

In the field of Artificial Intelligence, an agent is a system which is able to autonomously make decisions in order to reach a desired goal. As these systems grow more prevalent in our day-to-day lives, there has been an increased need to add explainability features which can provide an account for an agent's behavior. We therefore propose a framework that outlines how to produce comprehensible explanations for policy-aware agents, or agents which have rule-enforcing policies incorporated in their decision-making framework. This framework is designed using insights from the social sciences on how to produce good explanations. It is implemented in the Answer Set Programming language while using Python to assist with information extraction and natural-language translation. Because these agents incur penalties when violating policies, we are able to leverage these penalties to detect undesirable events in scenarios that are counterfactual to the agents' original actions. This lends itself to creating contrastive explanations (e.g., "the agent performed this action because, had it not, undesirable event X would have occurred."), which formulate the core component for our explainability framework. The framework is evaluated using a survey wherein human participants provide feedback on our program-generated explanations.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_239aca1b136af24dc4e17348