Microsoft 的研究透過反覆改寫任務原語、追蹤狀態與控制邏輯,在不訓練模型的情況下提升長上下文推理表現。
- - 基準結果:Llama3-8B 在長上下文基準上的平均分數提升 64.18 分。
- 為 Llama3-8B 建立的 harness 也能轉移至 Qwen2.5-3B。
AI 伴隨問答
針對這篇報導有疑問?可直接點選快捷問題或向 AI 追問背景脈絡與技術細節:
Learn to build a custom harness, folks.
This Microsoft work builds a harness to improve long-context reasoning without synthetic data or post-training.
(bookmark it)
They show that Llama3-8B gains 64.18 points on average across long-context benchmarks with no training at all. The gain comes from the harness.
It breaks long-context tasks into capability primitives. A strong agent then rewrites those primitives, the state they track, and the control logic over many rounds of self-improvement on a development set.
The harness built for Llama3-8B transfers to Qwen2.5-3B. On HELMET and RULER, it beats NExtLong and PolicyLong, which rely on data synthesis and training, at less than half their estimated cost.
The harness is written by GPT-5.6-Sol, and results drop sharply when the small models build their own.
The takeaway: before post-training a small model for long context, try improving the harness around it.
Chat with Paper: https://t.co/hSrVAp9Xyo