Metraipolis › archive › dc_75bf69fe7724

Smarter by the Moment: Environment-Driven Dynamic Policies for Continual LLM Improvement — arXiv:2609.16800

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.16800
License (as archived): CC0-1.0
Archived: 2026-10-15T19:19:19.337Z
SHA-256 of the archived text: 0304c34a3cddf82191283ad0090fa1daf9649081fbd4f63d99e5e1ea587baba6
Stable URL of this page: https://metraipolis.com/documento/dc_75bf69fe7724

How to cite

Smarter by the Moment: Environment-Driven Dynamic Policies for Continual LLM Improvement — arXiv:2609.16800 — arXiv (en), https://arxiv.org/abs/2609.16800 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_75bf69fe7724 (Metraipolis archive dc_75bf69fe7724, sha256 0304c34a3cddf82191283ad0090fa1daf9649081fbd4f63d99e5e1ea587baba6)

BibTeX

@misc{dc75bf69fe7724,
  title = {Smarter by the Moment: Environment-Driven Dynamic Policies for Continual LLM Improvement — arXiv:2609.16800},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.16800},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_75bf69fe7724; sha256 0304c34a3cddf82191283ad0090fa1daf9649081fbd4f63d99e5e1ea587baba6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.16800. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large Language Models (LLMs) have achieved remarkable progress across diverse domains, but continual adaptation to evolving tasks and environments remains a key challenge. Existing memory-augmented approaches retrieve individual past examples as direct references, but do not explicitly synthesize actionable strategies from them, causing the same types of errors to recur. We propose Dynamic Retrieval-based Policy Generation (DRPG), a framework that integrates memory-based retrieval with a dynamic policy generator, leveraging historical data and environment feedback to produce task-specific policies for continual LLM improvement. We evaluate DRPG across six benchmarks spanning text-to-SQL, question answering, medical diagnosis, and Python programming, using seven LLMs from both proprietary and open-weight families. DRPG outperforms strong baselines across most datasets and models. Further analysis demonstrates that DRPG's policy generation is robust to retrieval strategy, operates effectively without prior policy continuity, and can leverage smaller or cross-family models as cost-efficient policy generators. We also find that the benefit of policy-level guidance depends on task characteristics, offering practical insights into when and under what conditions this mechanism is most effective.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-16 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.16800 — 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 2026-10-15T18:32:32.831Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).