Strategist: Evolving Reasoning with Agents

A November 2, 2026 arXiv paper introduces Strategist, a meta-agent that evolves inference strategies by writing them as reusable executable "blueprints" and revising them against real samples. Across 30 benchmarks, Strategist beat the strongest baseline on 24 and matched its average accuracy (74.7% versus 74.0%) at 39% lower inference cost, with strategies transferring to unseen tasks and other models without further search. The work targets the hand-written half of agent systems — the reasoning procedure that turns model calls into a response — and lets that layer improve on its own.

Computer Science Artificial Intelligence Submitted on 2 Nov 2026 Title:Strategist: Evolving Reasoning with Agents View PDF http://arxiv.org/pdf/2611.03618v1 HTML experimental https://arxiv.org/html/2611.03618v1 Abstract: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. Additional Features References & Citations Loading... Bibliographic and Citation Tools Bibliographic Explorer What is the Explorer? https://info.arxiv.org/labs/showcase.html arxiv-bibliographic-explorer Connected Papers What is Connected Papers? https://www.connectedpapers.com/about Litmaps What is Litmaps? https://www.litmaps.co/ scite Smart Citations What are Smart Citations? https://www.scite.ai/ Code, Data and Media Associated with this Article alphaXiv What is alphaXiv? https://alphaxiv.org/ CatalyzeX Code Finder for Papers What is CatalyzeX? https://www.catalyzex.com DagsHub What is DagsHub? https://dagshub.com/ Gotit.pub What is GotitPub? http://gotit.pub/faq Hugging Face What is Huggingface? https://huggingface.co/huggingface ScienceCast What is ScienceCast? https://sciencecast.org/welcome Demos Recommenders and Search Tools Influence Flower What are Influence Flowers? https://influencemap.cmlab.dev/ CORE Recommender What is CORE? https://core.ac.uk/services/recommender arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs https://info.arxiv.org/labs/index.html .