跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-10AI 評分44

Vela:以用戶行為作為監督訊號,激發大語言模型智能

Vela: User Behavior as Supervision Sparks LLM Intelligence

AI 導讀

Vela 以真實用戶行為作為監督訊號,將行為資料轉化為訓練任務與軌跡,並用來微調 Qwen3.6-35B-A3B,提升其用戶相關能力。微調後,用戶相關任務最高提升 11.5 分,一般基準平均提升 4 分。微調後再進行強化學習,表現較從基礎模型開始進行強化學習最高提升 7.7 分。

正文

Published on Oct 10

Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

Large language models are increasingly deployed in applications that act on users' long-term behavior histories, from personal assistants to recommendation and advertising systems. These applications demand the user dimension of LLM intelligence: inferring a person's preferences, intent, and likely future actions from weeks to years of behavior data. Yet current models are trained on static text or synthetic data, neither of which captures how user behavior evolves over time. Real-world behavior records, already available at scale on content platforms and in personal-assistant agents, offer a natural supervisory signal. We propose user behavior as supervision and introduce Vela, a framework that converts real user behavior data into trainable tasks and trajectories. From the anonymized behavior records of 100,000 users, Vela generates 100,000 tasks across 91 real-world task templates; difficulty-based filtering and trajectory acceptance criteria retain approximately 75,000 tasks with selected training trajectories. Fine-tuning Qwen3.6-35B-A3B on these trajectories improves performance over the base model by up to 11.5 points on user-related tasks and by an average of 4 points on general benchmarks. Training on more user behavior data further improves user-related performance, and reinforcement learning after fine-tuning outperforms reinforcement learning from the base model by up to 7.7 points. These gains suggest that real-world user behavior is a scalable source of supervision for both user-centered capabilities and the broader intelligence of LLMs.

View arXiv page View PDF Project page GitHub Add to collection

Get this paper in your agent:

hf papers read 2610.14709

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/2610.14709 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/2610.14709 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/2610.14709 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