Using Autonomous Agents to Improve Efficiency and Robustness in Slow, Unreliable Networks
Bibliographic record
Abstract
and to use resources at that node. At EMAA's core lies a Dock that provides an execution environment for agents, handles incoming and outgoing agent transfers, and controls agent access to services. EMAA allows users to define agents, services, and events. Under the EMAA framework, agents are built from small, easily reused tasks that combine to meet a userOs goal. An agent's tasks are structured within an itinerary. Agents may be mobile, and typically use stationary services. Services may implement connections to external systems (e.g., databases or legacy applications), provide complex functionality, or carry out other functions, but they are not primary actors. Goal-oriented and directed activity is generally held to be the function of agents. Both agents and services may send and receive events. In the following subsections we discuss two EMAA features which support robust agent operation under undesirable conditions. Itineraries. EMAA itineraries are composed of states (each of which may contain one or more tasks) and transitions between states; they are structured as finite state machines. An EMAA agent contains internal memory that encodes data dependencies among tasks: the output of one task may be used as input to another task, etc. Itineraries employ some decision logic to determine whether and where to execute states. Some states must be executed on a specific machine, and others must be executed on any machine where the resources needed to support execution of the encapsulated task (or tasks) exist. Reliable Event Messaging. To address the need for remote control and execution monitoring of mobile agents, ATL developed the Event Transceiver Server (ETS), an event handler residing on each dock with registered listeners for agents. The ETS provides reliable event messaging for mobile objects, both sending and receiving. It is invaluable for remotely or locally controlling, monitoring, and retasking agents. DAIS: A Case Study and Problem Illustration
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 | 0.005 | 0.026 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.003 | 0.004 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 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".