Requester vs. Helper-Initiated Protocols for Mutual Assistance in Agent Teamwork
Bibliographic record
Abstract
The Mutual Assistance Protocol (MAP) enables members of an agent team to directly help each other whenever they jointly determine, through a bilateral distributed agreement, that such help is beneficial to the team. Its purpose is to improve the team's performance without affecting its existing organization. In this paper we define and investigate two versions of this generic protocol: the Requester-Initiated Action MAP, which enables team members to proactively seek help, and the Helper-Initiated Action MAP, which enables them to proactively offer help. In both cases, the help consists in performing an action on behalf of a teammate. We introduce the notions of individual well being, that helps an agent decide when to seek or offer help, and proximity bias, that favors assistance to agents which are close to an achievement for the team. Simulation experiments show that these design refinements result in team performance gains over the original version of Action MAP, as we vary the amount of agents' initial resources, dynamic disturbance in the environment, and communication costs. The results confirm the superior performance of teams with Action MAP protocols over teams without help mechanisms. The analysis shows that the relative strengths of the two protocols are complementary. This motivates research interest in protocols that allow proactive behavior of team members in both seeking and offering help.
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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".