Metraipolis › archive › dc_f24371709bc3

Strategist: Evolving Reasoning with Agents — arXiv:2611.03618

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.03618
License (as archived)
CC0-1.0
Archived
2026-11-03T10:44:26.432Z
SHA-256 of the archived text
23920bfe00b6624740ed8f3703d5129fab7868466a025875cd478d5ea621b0b4
Stable URL of this page
https://metraipolis.com/documento/dc_f24371709bc3

How to cite

Strategist: Evolving Reasoning with Agents — arXiv:2611.03618 — arXiv (en), https://arxiv.org/abs/2611.03618 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f24371709bc3 (Metraipolis archive dc_f24371709bc3, sha256 23920bfe00b6624740ed8f3703d5129fab7868466a025875cd478d5ea621b0b4)
BibTeX
@misc{dcf24371709bc3,
  title = {Strategist: Evolving Reasoning with Agents — arXiv:2611.03618},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.03618},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f24371709bc3; sha256 23920bfe00b6624740ed8f3703d5129fab7868466a025875cd478d5ea621b0b4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03618. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

A model is only half of an AI agent system. The other half is the inference strategy: the reasoning procedure that turns model calls into a response. Today that second half is written by hand, and the experience of building one strategy never carries to the next. We introduce Strategist, a meta-agent that evolves inference strategies across tasks. Each strategy is written as a blueprint,executable code that other strategies can reuse, and together the blueprints form a library. Given a task and a small development set, Strategist retrieves related blueprints, writes candidate strategies, tests them on real samples, and revises them from the results. Every candidate then enters the library, so later tasks build on earlier discoveries. On 30 benchmarks, Strategist beats the strongest baseline on 24 and matches its average accuracy (74.7% vs.74.0%) at 39% lower inference cost. Its strategies also transfer to unseen tasks and other models without further search. The part of an AI system that is not improved on its own now does.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2611.03618 — 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 2026-11-03T10:39:50.358Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).