Debugging Agent Programs with Why?: Questions
Michael Winikoff
- 08 May 2017
- pp 251-259
38
TL;DR: This paper develops and formalises definitions for "why?" and "why not?" questions and associated answers, and illustrates their application using a scenario.
read more
Abstract: Debugging is hard, and debugging cognitive agent programs is particularly hard, since they involve concurrency, a dynamic environment, and a complex execution model that includes failure handling Previous work by Ko & Myers has demonstrated that providing Alice and Java programmers with software that can answer "why?" and "why not?" questions can make a dramatic difference to debugging performance This paper considers how to adapt this approach to cognitive agent programs, specifically AgentSpeak It develops and formalises definitions for "why?" and "why not?" questions and associated answers, and illustrates their application using a scenario
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Explanation in artificial intelligence: Insights from the social sciences
TL;DR: This paper argues that the field of explainable artificial intelligence should build on existing research, and reviews relevant papers from philosophy, cognitive psychology/science, and social psychology, which study these topics, and draws out some important findings.
•Posted Content
Explanation in Artificial Intelligence: Insights from the Social Sciences
TL;DR: There has been a recent resurgence in the area of explainable artificial intelligence as researchers and practitioners seek to make their algorithms more understandable as mentioned in this paper, and it should not be controversial to say that looking at how humans explain to each other can serve as a useful starting point for explanation in artificial intelligence.
929
•Posted Content
Contrastive Explanation: A Structural-Model Approach
TL;DR: This model can help researchers in subfields of artificial intelligence to better understand contrastive explanation and is demonstrated on two classical problems in artificial intelligence: classification and planning.
Understanding artificial intelligence ethics and safety.
TL;DR: This guide identifies the potential harms caused by AI systems and proposes concrete, operationalisable measures to counteract them and builds out a vision of human-centred and context-sensitive implementation that gives a central role to communication, evidence-based reasoning, situational awareness, and moral justifiability.
84
•Proceedings Article
A Grounded Interaction Protocol for Explainable Artificial Intelligence
Prashan Madumal,Tim Miller,Liz Sonenberg,Frank Vetere +3 more
- 08 May 2019
TL;DR: This paper investigates the structural aspects of an interactive explanation to propose an interaction protocol and shows that the proposed model can closely follow the explanation dialogues of human-agent conversations.
43
References
•Book
Algorithmic Program Debugging
Ehud Shapiro
- 14 Apr 1983
TL;DR: An algorithm that can fix a bug that has been identified, and integrate it with the diagnosis algorithms to form an interactive debugging system that can debug programs that are too complex for the Model Inference System to synthesize.
1.2K
AgentSpeak(L): BDI agents speak out in a logical computable language
Anand S. Rao
- 01 Feb 1996
TL;DR: This paper provides an alternative formalization of BDI agents by providing an operational and proof-theoretic semantics of a language AgentSpeak(L), which can be viewed as an abstraction of one of the implemented BDI systems and allows agent programs to be written and interpreted in a manner similar to that of horn-clause logic programs.
Debugging reinvented: asking and answering why and why not questions about program behavior
Amy J. Ko,Brad A. Myers +1 more
- 10 May 2008
TL;DR: The Whyline is a new kind of debugging tool that enables developers to select a question about program output from a set of why did and why didn't questions derived from the program's code and execution.
316
Jadex: A BDI-Agent System Combining Middleware and Reasoning
Lars Braubach,Alexander Pokahr,Winfried Lamersdorf +2 more
- 01 Jan 2005
TL;DR: The Jadex reasoning engine is presented, which supports cognitive agents by exploiting the BDI model and is realized as adaptable extension for agent middleware such as the widely used JADE platform.
Evolutionary testing of autonomous software agents
Cu D. Nguyen,Anna Perini,Paolo Tonella,Simon Miles,Mark Harman,Michael Luck +5 more
- 10 May 2009
TL;DR: This paper proposes a methodology to derive objective (fitness) functions that drive evolutionary algorithms, and evaluates the overall approach with two simulated autonomous agents, showing that the approach is effective in finding good test cases automatically.