Optimizing agent-based meeting scheduling through preference estimation
Bibliographic record
Abstract
Meeting scheduling is a routine task that needs to be performed quite regularly and frequently within any organization. Unfortunately, this task can be quite tedious and time-consuming, potentially requiring a several rounds of negotiations among many people on the meeting date, time and place before a meeting can finally be confirmed. The objective of our research is to create an agent-based environment within which meeting scheduling can be performed and optimized. For meeting scheduling, we define optimality as the solution that has the highest average preference level among all the possible choices. Our model tries to mimic real life in that an individual's preferences are not made public. Without complete information, traditional optimal algorithms, such as A* will not work. In this paper, we present a novel “preference estimation” technique that allows us to find optimal solutions to negotiations problems without needing to know the exact preference models of all the meeting participants beforehand. Instead, their preferences are “estimated” and built on the fly based on observations of their responses during negotiation. Another unique contribution is the use of “preference rules” that allow preferences to change dynamical as scheduling decisions are made. This mimics changing preferences as schedule gets filled. This paper uses two negotiation algorithms to compare the effect of “preference estimation”—one that is based on negotiation through relaxation and the other that extends this with preference estimations. Simulations were then performed to compare these algorithms.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.003 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".