Think Harder Where It Matters: Item-Level Adaptive Recursion for Sequential Recommendation

Zhanshuo Cao, Jiakai Tang, Yuqi Zhou, Sunhao Dai, Jun Xu · 2026 · arXiv

DOI: 10.48550/arXiv.2610.30128 · open-access PDF

Arabic

عادة ما تخص الموصوفات التالية الحالية ميزانية حسابية ثابتة لكل نقطة في تاريخ تفاعل المستخدم ، بغض النظر عن مساهمة هذه النقطة في التوقيت النهائي. نحن نناقش هذا التصميم الفعلي مع نتائج تشخيصية اثنين. (1) حاجة حسابية غير متساوية: تختلف الوظائف في نفس الترتيب بشكل كبير في مقدار الحساب الذي يحتاجونه.

Machine translation (Meta M2M100); the English original follows.

Abstract

Existing sequential recommenders usually allocate a fixed computational budget to every item in a user's interaction history, regardless of the item's contribution to the final prediction. We challenge this de facto design with two diagnostic findings. (1) Non-uniform computational need: items within the same sequence vary drastically in how much computation they require. Most converge after shallow processing while a critical minority only stabilizes at full depth. (2) Suboptimality of fixed allocation: given oracle access to the target item, a non-uniform depth assignment consistently outran

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.30128, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange