首页/论文/2011.10707

arXiv 2011.107072020-11-21cs.AI

Explainable Composition of Aggregated Assistants

Arizona State University（亚利桑那州立大学）；IBM Research AI（IBM研究AI部门）

Sarath Sreedharan, Tathagata Chakraborti, Yara Rizk, Yasaman Khazaeni

英文摘要：

A new design of an AI assistant that has become increasingly popular is that of an "aggregated assistant" -- realized as an orchestrated composition of several individual skills or agents that can each perform atomic tasks. In this paper, we will talk about the role of planning in the automated composition of such assistants and explore how concepts in automated planning can help to establish transparency of the inner workings of the assistant to the end-user.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

PEAK：通过自动化知识提取实现可解释的隐私助手

PEAK: Explainable Privacy Assistant through Automated Knowledge Extraction

Bogazici University（海峡大学）；Amazon Alexa AI（亚马逊Alexa人工智能）；Utrecht University（乌得勒支大学）

本文提出PEAK隐私助手，通过潜在主题发现、解释类别识别和自动化解释生成，为隐私决策提供可理解解释，用户研究表明其解释有用易理解，并能提升隐私助手自身决策能力。

2023-05-31cs.AIcs.CRcs.HC

CueTip：一个交互式、可解释且具备物理感知能力的台球助手

CueTip: An Interactive and Explainable Physics-aware Pool Assistant

University of Edinburgh（爱丁堡大学）；Lightspeed Studios（光速工作室）；Independent Researcher（独立研究者）

本文提出 CueTip 台球助手，通过自然语言事件轨迹、物理感知推理、专家规则解释和神经适配器，实现可复用的交互式可解释教练功能。

2025-03-18cs.AIcs.HC

FFAA：基于多模态大语言模型的可解释开放世界人脸伪造分析助手

FFAA: Multimodal Large Language Model based Explainable Open-World Face Forgery Analysis Assistant

Tsinghua University（清华大学）；The Chinese University of Hong Kong（香港中文大学）；HKUST（香港科技大学）

本文针对开放世界人脸伪造分析中缺乏可解释性和鲁棒性的问题，提出FFAA助手，通过微调多模态大语言模型并结合多答案智能决策系统，在提供可解释结果的同时显著提升准确性与鲁棒性。

2024-11-21cs.AIcs.CV

面向入门编程教育的可解释AI助手：通过教师-AI协作提高反馈可靠性

An Explainable AI Assistant for Introductory Programming Education: Improving Feedback Reliability with Instructor-AI Collaboration

North Carolina State University（北卡罗来纳州立大学）；University of California, Berkeley（加州大学伯克利分校）

提出一种可解释AI驱动的课堂助手，通过分析学生代码、映射逻辑错误到教师识别的误解并提供教师撰写的反馈，提高入门编程课程中反馈的可靠性和可解释性。

2026-06-12cs.AIcs.CYcs.ET

波兰语儿童音素级发音错误筛查与可解释助手

Phoneme-Level Mispronunciation Screening in Polish-Speaking Children with an Explainable Assistant

AGH University of Krakow（克拉科夫AGH大学）；SoftServe（SoftServe公司）；Department of Biomedical Engineering, Silesian University of Technology（技术大学生物医学工程系）；Institute of Linguistics, Faculty of Humanities, University of Silesia in Katowice（卡托维兹大学人文学院语言学研究所）

提出一种针对波兰语儿童齿擦音替代错误的轻量级筛查流程，结合wav2vec2 CTC识别器与对齐错误分类，在10名儿童559个话语上达到88.7%精确序列匹配，筛查代理F1=0.67，误报率2.7%。

2026-06-25cs.AIcs.MAeess.AS

Fountain——一个结合知识表示与语言模型用于制造风险识别的智能上下文助手

Fountain -- an intelligent contextual assistant combining knowledge representation and language models for manufacturing risk identification

FORVIA Clean Mobility（佛吉亚清洁出行部门）

针对大批量生产中偏离设计或工艺带来的潜在风险，开发了集成于偏差管理流程的上下文助手Fountain。该系统结合微调语言模型与属性图知识表示，在标准CPU上即可提供可解释且一致的风险识别推荐，具备易部署性。

2023-08-01cs.AIcs.CL

更多相关论文收起更多论文

MemX：面向AI助手的本地优先长期记忆系统

MemX: A Local-First Long-Term Memory System for AI Assistants

Lizheng Sun（孙立政）

MemX是一种本地优先的长期记忆系统，通过向量召回、关键词召回和RRF等方法提升检索稳定性，实验表明其在中文基准测试中达到91.3%的Hit@1精度，且在长文本检索中表现出色。

2026-03-17cs.AIcs.IR

Visualizations for an Explainable Planning Agent

Computer Science Department, Arizona State University（亚利桑那州立大学计算机科学系）；IBM T. J. Watson Research Center（IBM T.J.沃森研究中心）

In this paper, we report on the visualization capabilities of an Explainable AI Planning (XAIP) agent that can support human in the loop decision making. Imposing transparency and explainability requirements on such agents is especially important in order to establish trust and common ground with the end-to-end automated planning system. Visualizing the agent's internal decision-making processes is a crucial step towards achieving this. This may include externalizing the "brain" of the agent -- starting from its sensory inputs, to progressively higher order decisions made by it in order to dri…

2018-02-08cs.AIcs.CYcs.HC

SuSketch: Surrogate Models of Gameplay as a Design Assistant

Institute of Digital Games, University of Malta（马耳他大学数字游戏研究所）

This paper introduces SuSketch, a design tool for first person shooter levels. SuSketch provides the designer with gameplay predictions for two competing players of specific character classes. The interface allows the designer to work side-by-side with an artificially intelligent creator and to receive varied types of feedback such as path information, predicted balance between players in a complete playthrough, or a predicted heatmap of the locations of player deaths. The system also proactively designs alternatives to the level and class pairing, and presents them to the designer as suggesti…

2021-03-22cs.AIcs.HCcs.LG