跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 28 天前AI 評分31

HaMo:面向長期持續學習的 Harness-Model 協作

Harness-Model Collaboration for Long-Horizon Continual Learning

AI 導讀

HaMo 提出一種 Harness-Model 協作框架,結合程序經驗卡片的快速檢索與模型的漸進式適應,以提升長期網絡智能體的經驗保留及跨任務執行能力。框架將軌跡提煉成策略級經驗卡片供即時檢索,並以經驗條件式持續學習訓練模型理解和執行策略。實驗顯示,HaMo 在域內及跨域轉移下均優於僅使用 harness 或僅作模型適應的方法,並提升保留與適應表現。

正文

Published on Oct 26

·

Submitted by

bizhen

on Oct 28

Authors:

,

,

,

,

,

,

,

Abstract

HaMo combines rapid retrieval of procedural experience cards with gradual model adaptation to improve long-horizon web agents' retention and cross-task execution.

Long-horizon agents continuously encounter reusable procedural knowledge, yet existing systems typically rely either on model adaptation or external memory, trading persistent learning for rapid reuse. This limitation is especially important for Web agents that repeatedly execute related multi-step workflows. We propose HaMo, a Harness-Model collaborative framework that combines fast non-parametric experience accumulation with slow parametric adaptation. HaMo distills trajectories into strategy-level experience cards for immediate retrieval, while an experience-conditioned continual learning objective trains the model to interpret, ground, and execute retrieved strategies across changing contexts. A retrieval-coverage-based selection mechanism further identifies compact and complementary trajectories for parameter updates. Experiments show that HaMo outperforms harness-only and model-only adaptation under within-domain and cross-domain shifts, improving both retention and adaptation. These results highlight the importance of jointly preserving procedural experience and internalizing the competence to transfer and execute it across tasks.

View arXiv page View PDF Add to collection

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.34724 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/2610.34724 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/2610.34724 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