IMAC: Intelligent Multi-Agent Content Steering for DASH
Bibliographic record
Abstract
Multi-CDN strategies are crucial for enhancing Quality of Experience (QoE) in adaptive video streaming. The recent development of the content steering standard (ETSI TS 103 998) facilitates real-time decision-making by gathering performance data from players and CDNs to select the best-performing CDN. Current CDN selection methods rely on heuristic approaches that struggle with network variability lack scalability and often result in extended switching delays and complex implementations, compromising QoE. It is imperative to develop a more robust CDN selection solution that can be generalizable to various network conditions and client demands. To fill this gap, we introduce IMAC, a learning-based multi-agent solution for real-time CDN selection applicable to both video-on-demand (VoD) and low-latency-live (LLL) streaming. Leveraging a deep reinforcement learning (DRL) framework aligned with the content steering standard, IMAC predicts optimal CDN policies in realtime. By coordinating multiple agents, it minimizes CDN switching delays, enhances reliability, and adapts to network conditions, content types, and viewer demands, ensuring seamless high-quality content delivery. Preliminary results show a ~24% VMAF improvement with a ~187% QoE increase and no rebuffering for VoD and a ~17% VMAF increase with ~186% better QoE and a ~23% reduction in rebuffering for LLL mode.
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 | 0.000 |
| Open science | 0.002 | 0.001 |
| 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".