Strategist: a meta-agent that evolves inference strategies as code, with 39% lower inference cost
Lu, Xu, Hua and Liu introduce Strategist, a meta-agent that writes inference strategies as “blueprints” — executable code that other strategies can reuse — and stores them in a library. For a given task and a small development set, it retrieves related blueprints, writes candidate strategies, tests them on real samples and revises them from the results. According to the authors' abstract, across 30 benchmarks Strategist beats the strongest baseline on 24; average accuracy is 74.7% vs 74.0% at 39% lower inference cost, and strategies transfer to unseen tasks and other models without further search.
Source: arXiv
Need an LLM chatbot or agent for your business?
Describe your need briefly; you will get clarifying questions and a scoped proposal before any work starts.
Related news
AI & LLM · 2026-11-04
Tencent releases Hy4: first vision and computer-use support, aimed at the top tier of open models
AI & LLM · 2026-11-03
LeanGuard: checking every tool call of an LLM agent against a policy written in Lean 4
AI & LLM · 2026-11-03