Bibliographic record
Abstract
Software agents are well-suited to assisting users with routine, repetitive, and time-consuming tasks in various educational environments. In order to achieve complex tasks effectively, humans and agents sometimes need to work together. However, some issues in human agent interaction have not been solved properly, such as delegation, trust and privacy. The agent research community has focused on technologies for constructing autonomous agents and techniques for collaboration among agents. Little attention has been paid to supporting interactions between humans and agents. p* The objectives of this research are to investigate how easy it might be for a user to program his/her agent, how users behave when given the ability to program their agents, whether access to necessary help resources can be improved, and whether such a system can facilitate collaborative learning. Studying users’ concerns about their privacy and how an online learning environment can be built to protect users’ privacy are also interesting issues to us. In this thesis two alternative systems were developed for programmable agents in which a human user can define a set of rules to direct an agent’s activities at execution time. The systems were built on top of a multi-agent collaborative learning environment that enables a user to program his or her agent to communicate with other agents and to monitor the activities of other users and their agents. These systems for end user programmable agents were evaluated and compared. The result demonstrated that an end-user programming environment is able to meet users’ individual needs on awareness information, facilitate the information exchange among the users, and enhance the communication between users within a virtual learning environment. This research provides a platform for investigating concerns over user privacy caused by agent programmability.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".