Metraipolis › archive › dc_f529fbaf24db

Navigation-Informed Embeddings: Dense-Retriever Adaptation from Agent Search Traces — arXiv:2608.15956

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.15956
License (as archived)
CC0-1.0
Archived
2026-10-18T17:33:26.289Z
SHA-256 of the archived text
16e475ef2588fd25f5626d152af396a364c0c2e43e875ddb7dadb8cba574960d
Stable URL of this page
https://metraipolis.com/documento/dc_f529fbaf24db

How to cite

Navigation-Informed Embeddings: Dense-Retriever Adaptation from Agent Search Traces — arXiv:2608.15956 — arXiv (en), https://arxiv.org/abs/2608.15956 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f529fbaf24db (Metraipolis archive dc_f529fbaf24db, sha256 16e475ef2588fd25f5626d152af396a364c0c2e43e875ddb7dadb8cba574960d)
BibTeX
@misc{dcf529fbaf24db,
  title = {Navigation-Informed Embeddings: Dense-Retriever Adaptation from Agent Search Traces — arXiv:2608.15956},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.15956},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f529fbaf24db; sha256 16e475ef2588fd25f5626d152af396a364c0c2e43e875ddb7dadb8cba574960d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15956. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Agentic retrieval workflows produce query, retrieval, and stopping traces as a byproduct of answering questions. We study how these traces can adapt a deployed dense retriever to changing workflow distributions without new relevance labels, synthetic queries, or LLM judgments. We introduce Navigation-Informed Embeddings (NIE), a family of trace-derived objectives. NIE-Stop turns the stopping document into a soft positive; NIE-Path additionally uses preceding path documents as hard comparisons and imposes ordinal constraints with geometric decay. A BGE encoder adapted from retained source trajectories improves support Recall@20 on an independent target benchmark from 72.2 to 78.0 overall. NIE-Stop reaches 76.9 overall and 52.3 on long paths; NIE-Path raises long-path performance to 55.4, compared with 46.7 for the unadapted encoder. A shuffled-order control under the full path objective loses 3.2 points. Without public-benchmark training, the same adapter also improves nDCG@10 by 1.9 points on standard BEIR HotpotQA. NIE therefore provides a lightweight adaptation channel for settings where trajectories are already retained, with zero incremental labeling cost.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.15956 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T16:29:13.843Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).