ClawRec: A Claw-Native Recommender System

2026-07-26

AI Summary

Traditional recommender systems are confined to single platforms and struggle to support users’ cross-platform task needs in multi-source environments. This work proposes Claw-native recommendation, a novel paradigm that introduces the first native recommendation architecture tailored for Claw-style personal agents. The approach organizes retrieval through functional source roles, prunes redundant candidates based on marginal utility, and models user states via evidence linking and temporal structuralization to achieve coherent alignment between cross-platform behaviors and multi-source content. Evaluated on the newly constructed benchmark ClawRec-SimBench, the method achieves an NDCG@20 of 0.6134 (+0.1126) and Hit@20 of 0.6944 (+0.0854), significantly outperforming the strongest baseline while simultaneously enhancing user state quality and temporal consistency.

Abstract

Recommender systems have become integral to navigating the modern digital ecosystem. Yet most deployed systems remain confined within single-platform boundaries, observing localized interaction traces and ranking items from isolated candidate spaces. This design is poorly suited to real-world tasks that unfold through searches, content consumption, and comparisons across multiple information sources. Claw-style personal agents, with persistent access to authorized cross-platform context, create an opportunity for recommendation to operate around the user rather than any single platform. In this paper, we introduce Claw-native recommender systems, a new paradigm that moves beyond platform-local ranking to produce unified, complementary recommendation slates spanning diverse sources and content forms. To instantiate this paradigm, we present ClawRec, the first recommender system designed to operate natively in this environment. ClawRec maintains an evidence-linked, temporally structured user state that connects cross-platform behaviors with cross-source recommendations. It organizes retrieval around functional source roles and selects candidates according to their marginal utility, producing non-redundant slates aligned with the user's active task. To enable rigorous evaluation, we introduce ClawRec-SimBench, a benchmark constructed from sequences of concrete life events and cross-platform behavior trajectories. Experiments show that ClawRec outperforms the strongest baselines, achieving an NDCG@20 of 0.6134 (+0.1126) and a Hit@20 of 0.6944 (+0.0854), while also improving user state quality and temporal alignment. Our code and dataset are available at https://github.com/RUCAIBox/ClawRec.

Problem

• cross-platform recommendation
• multi-source recommendation
• user task alignment
• recommendation personalization
• digital ecosystem navigation

Innovation

• Claw-native recommendation
• cross-platform user modeling
• evidence-linked user state
• marginal utility-based retrieval
• unified recommendation slate