Explainable Agents (XAg) by Design. Rodriguez, S. & Thangarajah, J. In Proceedings of the 2024 International Conference on Autonomous Agents and Multiagent Systems (Blue Sky), of AAMAS '24, pages 2712–2716, Auckland, New Zeland, 2024. ![Explainable Agents (XAg) by Design [pdf]](https://bibbase.org/img/filetypes/pdf.svg "pdf")
Paper abstract bibtex 2 downloads The likes of ChatGPT has propelled the use of AI techniques beyond our community’s expectations. Along with this, the fear of AI has also risen, in particular around the ability, or lack thereof, of the AI system to explain its behaviours. Explainability is a key element of building trust and an important issue for our community. In this paper we advocate for agents that are explainable-by-design, that is, explainability is built into the development of agents rather than an afterthought. We propose key features of an explainable agent (XAg) system and propose a general framework that enables explainability. We advocate the use of design patterns to develop XAgs and propose a general design pattern that can be used for any agent architecture. We instantiate our framework for goal-based agents and implement the framework for the SARL agent programming language coupled with a state-of-the-art event management system. We make a call to the developers of other agent programming languages (APLs) in our community to follow suit by instantiating the general framework we propose into their APL, perhaps even enhancing the framework we present. We also propose an open repository of design patterns and examples for agent systems. If nothing else, we hope this paper will inspire further work on XAg from the design perspective as it is critical that multi agent systems are explainable by design!
@inproceedings{Rodriguez2024XAgBlueSky,
address = {Auckland, New Zeland},
series = {{AAMAS} '24},
title = {Explainable {Agents} ({XAg}) by {Design}},
url = {https://www.ifaamas.org/Proceedings/aamas2024/pdfs/p2712.pdf},
abstract = {The likes of ChatGPT has propelled the use of AI techniques beyond
our community’s expectations. Along with this, the fear of AI has
also risen, in particular around the ability, or lack thereof, of the AI
system to explain its behaviours. Explainability is a key element of
building trust and an important issue for our community. In this
paper we advocate for agents that are explainable-by-design, that is,
explainability is built into the development of agents rather than an
afterthought. We propose key features of an explainable agent (XAg)
system and propose a general framework that enables explainability.
We advocate the use of design patterns to develop XAgs and propose
a general design pattern that can be used for any agent architecture.
We instantiate our framework for goal-based agents and implement
the framework for the SARL agent programming language coupled
with a state-of-the-art event management system. We make a call to
the developers of other agent programming languages (APLs) in our
community to follow suit by instantiating the general framework
we propose into their APL, perhaps even enhancing the framework
we present. We also propose an open repository of design patterns
and examples for agent systems. If nothing else, we hope this paper
will inspire further work on XAg from the design perspective as it
is critical that multi agent systems are explainable by design!},
booktitle = {Proceedings of the 2024 {International} {Conference} on {Autonomous} {Agents} and {Multiagent} {Systems} ({Blue} {Sky})},
author = {Rodriguez, Sebastian and Thangarajah, John},
year = {2024},
pages = {2712--2716},
}
Downloads: 2
{"_id":"FMdABqkKPqohJTquR","bibbaseid":"rodriguez-thangarajah-explainableagentsxagbydesign-2024","author_short":["Rodriguez, S.","Thangarajah, J."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","address":"Auckland, New Zeland","series":"AAMAS '24","title":"Explainable Agents (XAg) by Design","url":"https://www.ifaamas.org/Proceedings/aamas2024/pdfs/p2712.pdf","abstract":"The likes of ChatGPT has propelled the use of AI techniques beyond our community’s expectations. Along with this, the fear of AI has also risen, in particular around the ability, or lack thereof, of the AI system to explain its behaviours. Explainability is a key element of building trust and an important issue for our community. In this paper we advocate for agents that are explainable-by-design, that is, explainability is built into the development of agents rather than an afterthought. We propose key features of an explainable agent (XAg) system and propose a general framework that enables explainability. We advocate the use of design patterns to develop XAgs and propose a general design pattern that can be used for any agent architecture. We instantiate our framework for goal-based agents and implement the framework for the SARL agent programming language coupled with a state-of-the-art event management system. We make a call to the developers of other agent programming languages (APLs) in our community to follow suit by instantiating the general framework we propose into their APL, perhaps even enhancing the framework we present. We also propose an open repository of design patterns and examples for agent systems. If nothing else, we hope this paper will inspire further work on XAg from the design perspective as it is critical that multi agent systems are explainable by design!","booktitle":"Proceedings of the 2024 International Conference on Autonomous Agents and Multiagent Systems (Blue Sky)","author":[{"propositions":[],"lastnames":["Rodriguez"],"firstnames":["Sebastian"],"suffixes":[]},{"propositions":[],"lastnames":["Thangarajah"],"firstnames":["John"],"suffixes":[]}],"year":"2024","pages":"2712–2716","bibtex":"@inproceedings{Rodriguez2024XAgBlueSky,\n\taddress = {Auckland, New Zeland},\n\tseries = {{AAMAS} '24},\n\ttitle = {Explainable {Agents} ({XAg}) by {Design}},\n\turl = {https://www.ifaamas.org/Proceedings/aamas2024/pdfs/p2712.pdf},\n\tabstract = {The likes of ChatGPT has propelled the use of AI techniques beyond\nour community’s expectations. Along with this, the fear of AI has\nalso risen, in particular around the ability, or lack thereof, of the AI\nsystem to explain its behaviours. Explainability is a key element of\nbuilding trust and an important issue for our community. In this\npaper we advocate for agents that are explainable-by-design, that is,\nexplainability is built into the development of agents rather than an\nafterthought. We propose key features of an explainable agent (XAg)\nsystem and propose a general framework that enables explainability.\nWe advocate the use of design patterns to develop XAgs and propose\na general design pattern that can be used for any agent architecture.\nWe instantiate our framework for goal-based agents and implement\nthe framework for the SARL agent programming language coupled\nwith a state-of-the-art event management system. We make a call to\nthe developers of other agent programming languages (APLs) in our\ncommunity to follow suit by instantiating the general framework\nwe propose into their APL, perhaps even enhancing the framework\nwe present. We also propose an open repository of design patterns\nand examples for agent systems. If nothing else, we hope this paper\nwill inspire further work on XAg from the design perspective as it\nis critical that multi agent systems are explainable by design!},\n\tbooktitle = {Proceedings of the 2024 {International} {Conference} on {Autonomous} {Agents} and {Multiagent} {Systems} ({Blue} {Sky})},\n\tauthor = {Rodriguez, Sebastian and Thangarajah, John},\n\tyear = {2024},\n\tpages = {2712--2716},\n}\n\n","author_short":["Rodriguez, S.","Thangarajah, J."],"key":"Rodriguez2024XAgBlueSky","id":"Rodriguez2024XAgBlueSky","bibbaseid":"rodriguez-thangarajah-explainableagentsxagbydesign-2024","role":"author","urls":{"Paper":"https://www.ifaamas.org/Proceedings/aamas2024/pdfs/p2712.pdf"},"metadata":{"authorlinks":{}},"downloads":2},"bibtype":"inproceedings","biburl":"https://api.zotero.org/users/629018/collections/IH38WM4M/items?key=6tmWCKu5rNjpMYBCLquGea4A&format=bibtex&limit=100","dataSources":["dpS26Nm5wBb9pZTfk","yeCWMsXdeEPFrdJ8M"],"keywords":[],"search_terms":["explainable","agents","xag","design","rodriguez","thangarajah"],"title":"Explainable Agents (XAg) by Design","year":2024,"downloads":2}