Introspective Self-Explanation in Analytical Agents
نویسندگان
چکیده
There is a critical and urgent need for automated analytical agents operating in complex domains to provide meta-level explanations of their reasoning and conclusions. In this paper, we identify the principles for designing analytical agents that can explain their reasoning and justify their conclusions at different levels of abstractions to potential human customers with varying goals. We also analyze the goals of users of an automated agent for investigative analysis along the dimensions of why, what, how and when, and develop a taxonomy of human goals that will leverage the explanations generated by the agent.
منابع مشابه
Introspective Self-Explanations for Report Generation in Intelligence Analysis
Report generation is an integral part of many analytical tasks such as intelligence analysis. Thus, an important issue in developing cognitive assistants for analytical tasks is how the cognitive assistant may help a human analyst in generating reports. In this paper, we first describe the task of report generation in intelligence analysis. Then, we describe a scheme for enabling a cognitive as...
متن کاملExtending Introspective Learning from Self-Models
This position paper presents open issues for using self-models to guide introspective learning, focusing on five key types of areas to explore: (1) broadening the range of learning focuses and the range of learning tools which may be brought to bear, (2) learning for self-understanding as well as self-repair, (3) making model-based approaches more sensitive to processing characteristics, instea...
متن کاملLogical Theories for Agent Introspection
Thomas Bolander: Logical Theories for Introspective Agents Artificial intelligence systems (agents) generally have models of the environments they inhabit which they use for representing facts, for reasoning about these facts and for planning actions. Much intelligent behaviour seems to involve an ability to model not only one’s external environment but also oneself and one’s own reasoning. We ...
متن کاملMaximal Introspection of Agents
This paper concerns the representation of introspective belief and knowledge in multi-agent systems. An introspective agent is an agent that has the ability to refer to itself and reason about its own beliefs. It is well-known that representing introspective beliefs is theoretically very problematic. An agent which is given strong introspective abilities is most likely to have inconsistent beli...
متن کاملPreserved Self-Evaluation in Amnesia Supports Access to the Self through Introspective Computation
Encounters with new people result in the extraction and storage in memory of both their external features, allowing us to recognize them later, and their internal traits, allowing us to better control our current interactions with them and anticipate our future ones. Just as we extract, encode, store, retrieve and update the representations of others so, too, do we process representations of ou...
متن کامل