{
  "abstract": "Semantic communication jointly optimizes inference accuracy, channel use, and computation, yet the underlying communication program is typically specified before training. This paper presents ComRSI (Communications-Oriented Recursive Self-Improvement), a framework for recursively evolving that program through large-language-model-assisted code edits. A fixed agent modifies the encoder, channel adapters, decoder, loss, and training policy; a protected evaluator screens candidates under prescribed budgets and resource constraints. Accepted code and textual feedback inform subsequent proposals, while candidate weights are trained from scratch. In the original ten-generation CIFAR-100 lineage, eight accepted revisions produce an attention-pooled code achieving 74.3% test accuracy over an Additive White Gaussian Noise (AWGN) channel at 32 complex symbols per image, compared with 67.2% at 256 symbols for the initial design. The program also improves fading-channel accuracy and transfers to Tiny-ImageNet after retraining. A repeat study with ten searches per method compares ComRSI against non-recursive agents with and without textual history. Mean final search scores balancing accuracy, transmission rate, and computational cost are 0.7587, 0.7376, and 0.7089, respectively; the mean numbers of accepted revisions per search are 6.0, 5.0, and 2.1. The advantage over the memoryless agent is supported by a two-sided rank test, whereas the difference from the history-equipped agent remains statistically inconclusive at this sample size. Archived proposals show that pooling can yield a large improvement, while retained history supports subsequent refinement. These results support recursive program optimization within the evaluated setting and expose its remaining rate-robustness and compute-placement trade-offs.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.29641",
  "author_total": 8,
  "authors": [
    {
      "name": "Yan Gong"
    },
    {
      "name": "Zheng Chu"
    },
    {
      "name": "Wei Koong Chai"
    },
    {
      "name": "Hari Mohan Pandey"
    },
    {
      "name": "Jingrui Hou"
    },
    {
      "name": "Miao Zhang"
    },
    {
      "name": "Yuanjian Li"
    },
    {
      "name": "Pei Xiao"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/20n5s4k1d32x4.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.29641",
  "fulltext_url": null,
  "id": "20n5s4k1d32x4",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.29641",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.IT"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "eess.SP"
    ],
    [
      "arxiv",
      "math.IT"
    ],
    [
      "openalex",
      "1702|Evolutionary Algorithms and Applications"
    ]
  ],
  "openalex": "W7223217538",
  "pdf_url": "https://arxiv.org/pdf/2610.29641",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-21",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/20n5s4k1d32x4.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:34:22Z",
      "native_id": "2610.29641",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.29641"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:math.IT",
      "subfield": "general"
    }
  ],
  "title": "Recursive Code Evolution for Task-Oriented Semantic Communications",
  "title_text": "Recursive Code Evolution for Task-Oriented Semantic Communications",
  "type": "preprint",
  "updated_at": "2026-11-04T15:20:52Z",
  "url": "https://research.draconitic.com/paper/20n5s4k1d32x4",
  "venue": "arXiv",
  "versions": []
}