跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-02AI 評分38

Harness-Aware Distillation for Small Language Model Agents

Harness-Aware Distillation for Small Language Model Agents

AI 導讀

Harness-Aware Distillation(HAD)聚焦蒸餾教師模型在 harness 之外提供的能力,讓小型語言模型智能體學習如何正確運用 harness 資訊。HAD 在 on-policy 蒸餾上加入動作偏好比較和有效性檢查,無需任務獎勵、成功標籤或未來資訊。多項長時程智能體基準測試顯示,在相同固定 harness 下,HAD 優於 on-policy 蒸餾基線。

正文

Published on Oct 2

Authors:

,

,

Abstract

Language model agents are deployed with a harness, the software around the model that manages its context, tools, and feedback. When such an agent is distilled into a smaller one, the harness stays in place, so the student mainly needs the teacher-specific abilities that the harness cannot provide, such as acting correctly on harness information. Standard distillation, however, imitates the teacher's full outputs and treats the harness as part of the input. We propose Harness-Aware Distillation (HAD), which focuses distillation on what the teacher adds beyond the harness. HAD complements on-policy distillation with two components: an action preference that contrasts the same teacher's actions with and without the harness information, scored after the student's own reasoning, and a validity check that drops preference pairs whose preferred action contradicts the harness records. We show that the contrast gives the student information that imitating the teacher alone cannot provide, and HAD needs no task rewards, success labels, or future information. Across multiple long-horizon agent benchmarks and models, HAD outperforms on-policy distillation baselines with the same fixed harness. Our analysis shows that HAD enters fewer unproductive loops and recovers from errors more often than the baselines, and suggests that it adaptively keeps learnable feedback in its weights while reading state information from the harness.

View arXiv page View PDF Project page GitHub Add to collection

Get this paper in your agent:

hf papers read 2610.02858

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.02858 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.02858 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.02858 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co