Who Am I?: Towards Social Self-Awareness for Intelligent Agents
Authors: Budhitama Subagdja, Han Yi Tay, Ah-Hwee Tan
IJCAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | A practical framework for developing an agent architecture with this model of self and self-awareness is proposed allowing self to be ascribed to an existing intelligent agent architecture in general to enable its social ability, interactivity, and co-presence with others. Possible applications are discussed with some exemplifying cases based on an implementation of a conversational agent. The self-aware agent model has been implemented as an agent application to carry out Individual Cognitive Stimulation Therapy or ICST |
| Researcher Affiliation | Academia | 1Joint NTU-UBC Research Centre of Excellence in Active Living for the Elderly, 2School of Computer Science and Engineering, Nanyang Technological University, Singapore 3School of Information Systems, Singapore Management University budhitama@ntu.edu.sg, c160103@e.ntu.edu.sg, ahtan@smu.edu.sg |
| Pseudocode | Yes | Algorithm 1 Executive Process Operation Cycle |
| Open Source Code | No | The paper does not contain any explicit statements about releasing source code or links to a code repository. |
| Open Datasets | No | The paper describes an application in Individual Cognitive Stimulation Therapy (ICST) and provides dialog excerpts from interaction with a 'user', indicating data was used or collected. However, it does not provide concrete access information (link, DOI, citation) for a publicly available or open dataset. |
| Dataset Splits | No | The paper describes exemplified cases and dialog excerpts but does not provide specific details on training, validation, or test dataset splits (e.g., percentages, sample counts, or references to predefined splits). |
| Hardware Specification | No | The paper does not provide any specific details about the hardware used to run the experiments or implement the model. |
| Software Dependencies | No | The paper mentions components like a 'natural language parser' and 'natural language generation module' but does not specify any software names with version numbers. |
| Experiment Setup | No | The paper describes the functional components of the conversational agent (e.g., Natural Language Parser, Natural Language Generation Module, Dialog Manager) and how it handles conversation strategies. However, it does not provide specific experimental setup details such as hyperparameters, optimizer settings, or explicit training configurations. |