{
  "abstract": "Replay selectors often rank cached trajectories by format feedback, confidence, freshness, or response length, although cache-level correctness and downstream learner utility are distinct objectives. We formalize this selection-to-learning gap and introduce FAER as an auditable full-trajectory replay framework. Its training-free fixed selector is a protocol baseline; FAER-UTILITY is the learner-aware selector fitted on disjoint calibration blocks. The normalized gradient alignment is reported as a baseline, while a disposable optimizer-aware virtual update supplies a magnitude-aware utility surface. The audit contract freezes observed fields and replay traces before evaluation labels are joined. On GSM8K with Qwen2.5-1.5B-Instruct, the matched learner study reports quality 0.6329 for the fixed selector, compared with 0.5482 for uniform and 0.6037 for format-feedback under 128 updates. Metadata-only cross-fitted calibration reaches $0.6476\\!\\pm\\!0.0139$ over eight seeds (median 0.6481; paired 95% interval $[+0.079,+0.122]$) at 63,276 target-run tokens; its recorded full cost is 189,642 tokens and 3.48 GPU-hours including calibration. The completed FAER-UTILITY row reaches 0.6624 at 62,844 target-run tokens and 4.26 GPU-hours. Format-feedback selects records with correctness 0.6953, compared with 0.3594 for the fixed selector, despite the different downstream ranking. The completed comparison surfaces report the learner-aware ablation, same-seed gap, policy-optimization rows, and strict zero-shot transfer.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.00385",
  "author_total": 7,
  "authors": [
    {
      "name": "Miaobo Hu"
    },
    {
      "name": "Shuhao Hu"
    },
    {
      "name": "Xiaobo Guo"
    },
    {
      "name": "Xin Wang"
    },
    {
      "name": "Bokun Wang"
    },
    {
      "name": "Tianshu Fu"
    },
    {
      "name": "Daren Zha"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/0w0th7518ehjf.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.00385",
  "fulltext_url": null,
  "id": "0w0th7518ehjf",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.00385",
  "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.AI"
    ],
    [
      "arxiv",
      "cs.CL"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "1702|Topic Modeling"
    ]
  ],
  "openalex": "W7219155399",
  "pdf_url": "https://arxiv.org/pdf/2610.00385",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-16",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/0w0th7518ehjf.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:30:43Z",
      "native_id": "2610.00385",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.00385"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "FAER: Auditable Utility-Aligned Trajectory Replay for Language Model Post-Training",
  "title_text": "FAER: Auditable Utility-Aligned Trajectory Replay for Language Model Post-Training",
  "type": "preprint",
  "updated_at": "2026-10-30T12:33:38Z",
  "url": "https://research.draconitic.com/paper/0w0th7518ehjf",
  "venue": "arXiv",
  "versions": []
}