{
  "id": 3242,
  "url": "https://arxiv.org/abs/2606.04039v1",
  "title": "Beyond Static Priors: Dynamic Neural Guidance for Large-Scale Ant Colony Optimization",
  "summary": "Neural-guided Ant Colony Optimization (ACO) suffers from a fundamental training-inference misalignment: policies are typically trained to generate static priors (e.g., heatmaps), yet deployed to guide iterative, long-horizon search processes. In this paper, we present DyNACO, a novel framework that achieves dynamic neural guidance by periodically observing the pheromone distribution and the incumbent solution. To make DyNACO tractable at scale, we pair the policy with a perturbation-based ACO ba",
  "authors": "Dat Thanh Tran, Van Khu Vu, Yining Ma",
  "category": "research",
  "topics": "regulation,safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-06-02T03:32:36.000Z",
  "fetched_at": "2026-07-14T16:30:05.532Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/3242",
  "original_url": "https://arxiv.org/abs/2606.04039v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}