Intelligent Information Retrieval Using a Mobile Agents: A Proximal Policy Optimization Approach in Dynamic Networks
Bibliographic record
Abstract
not-yet-known not-yet-known not-yet-known unknown Efficient information retrieval in distributed and dynamic networks remains a critical challenge, as data is often scattered across multiple nodes with varying topologies and conditions. Mobile Intelligent Agents (MIAs) require adaptive and robust routing mechanisms to optimize performance metrics such as latency, energy consumption, and throughput. This study introduces the Information Retrieval Mobile Agent (IRMA) framework, which leverages Proximal Policy Optimization (PPO), a deep reinforcement learning (RL) algorithm, for adaptive routing of Mobile Intelligent Agents (MIAs) to dynamically navigate networks and retrieve data. PPO’s stable and efficient policy updates make it ideal for continuous state-action spaces in complex environments. We address critical challenges in distributed information retrieval, demonstrating significant improvements over traditional methods. We address critical challenges in distributed information retrieval, demonstrating significant improvements over traditional methods. Our novel application of PPO to MIA routing offers superior adaptability and performance compared to conventional techniques. Experimental results show that IRMA achieves lower latency, reduced energy consumption, and higher success rates in various network scenarios significantly outperforms competing methods in various metrics, making it robust solution for information retrieval in modern distributed networks.
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) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".