Metraipolis › archive › dc_660c021cf094

InsightEmb: Learning Action-Intent Embeddings for Agentic Insight Retrieval — arXiv:2608.04761

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.04761
License (as archived): CC0-1.0
Archived: 2026-10-31T11:14:36.008Z
SHA-256 of the archived text: 062030bf4dd36f6c04eb8258e7c9e4edfbf393e7060fae2a26ee83aa9f7d5001
Stable URL of this page: https://metraipolis.com/documento/dc_660c021cf094

How to cite

InsightEmb: Learning Action-Intent Embeddings for Agentic Insight Retrieval — arXiv:2608.04761 — arXiv (en), https://arxiv.org/abs/2608.04761 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_660c021cf094 (Metraipolis archive dc_660c021cf094, sha256 062030bf4dd36f6c04eb8258e7c9e4edfbf393e7060fae2a26ee83aa9f7d5001)

BibTeX

@misc{dc660c021cf094,
  title = {InsightEmb: Learning Action-Intent Embeddings for Agentic Insight Retrieval — arXiv:2608.04761},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.04761},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_660c021cf094; sha256 062030bf4dd36f6c04eb8258e7c9e4edfbf393e7060fae2a26ee83aa9f7d5001},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04761. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Self-improving agents accumulate reusable insights from prior trajectories, making retrieval increasingly important for turning accumulated experience into actionable guidance. At each decision step, retrieving the right insight can help the agent progress toward its goal, a setting we refer to as agentic insight retrieval. However, existing retrieval methods primarily model semantic similarity, while overlooking whether a retrieved insight resolves the agent's current decision bottleneck. We propose InsightEmb, a contrastive embedding framework that learns transferable progress-oriented retrieval geometry using only mathematical reasoning data. InsightEmb jointly learns to align concrete situations with abstract heuristic rules and to cluster reasoning trajectories with similar progress structures. We evaluate InsightEmb on dynamic agent tasks and a static skill-retrieval benchmark. Without any environment-specific training, InsightEmb improves over all these evaluations, surpassing the performance of existing reasoning embedding models. These results suggest that the geometry of state-insight matching can transfer across domains, enabling effective training from publicly available reasoning data without expensive environment-specific supervision.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-06 in cs.AI).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.04761 — 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 2026-10-31T11:02:13.546Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).