AI Paper Atlas

Research map / Large language models / Reasoning and chain of thought

MSR-Rec: Multi-Step Reasoning-Enhanced LLM for Sequential Recommendation

Tuo Wang, Meng Jian, Ge Shi, Lifang Wu, Yashen Wang

AAAI 2026 · Large language models › Reasoning and chain of thought · approach: Search and self-correction in reasoning · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes MSR-Rec, an LLM-based sequential recommender that aims to activate multi-step reasoning despite the lack of explicit reasoning supervision in implicit interaction data.

Problem

LLM-based sequential recommendation lacks explicit reasoning supervision because implicit user-item interactions do not provide reasoning traces, so LLMs' multi-step reasoning is not activated.

Approach

Uses multi-step reasoning enhancement for LLM-based sequential recommendation to supply reasoning supervision where implicit interactions provide none; the abstract is truncated, so the specific mechanism is not stated.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add synthesized reasoning data to fine-tuning (ablation)MSR-Rec · ElectronicsHitRatio@1: 0.3613 -> 0.4453Improved
add synthesized reasoning data to fine-tuning (ablation)MSR-Rec · HomeHitRatio@1: 0.2980 -> 0.3453Improved
add synthesized reasoning data to fine-tuning (ablation)MSR-Rec · HealthHitRatio@1: 0.4393 -> 0.4513Improved
add synthesized reasoning data to fine-tuning (ablation)MSR-Rec · ElectronicsGPTScore: 65.55 -> 82.35Improved
use bidirectional adaptive fusion instead of full reasoning chain at inference (ablation)MSR-Rec · ElectronicsHitRatio@1: 0.4220 -> 0.4453Improved
use full complex reasoning chain at inference instead of fusion (ablation)MSR-Rec · ElectronicsGPTScore: 82.35 -> 85.25Improved
add adaptive fusion over user-side-only reasoning (ablation)MSR-Rec · ElectronicsHitRatio@1: 0.4407 -> 0.4453Improved
add adaptive fusion over item-side-only reasoning (ablation)MSR-Rec · HomeHitRatio@1: 0.3373 -> 0.3453Improved
add adaptive fusion over item-side-only reasoning (ablation)MSR-Rec · ElectronicsGPTScore: 86.86 -> 82.35Hurt
fine-tune with reasoning (MSR-Rec) vs plain fine-tuned LLaRAMSR-Rec · ElectronicsHitRatio@1: 0.3400 -> 0.4453Improved
reduce the reasoning-to-recommendation loss weight ratio from 0.7/0.3 (ablation)MSR-Rec · Electronics, Home, HealthHitRatio@1Hurt
fine-tune Llama3-8B with reasoning supervisionMSR-Rec · ElectronicsValidRatio: 0.3300 -> 0.9653Improved

Limitations

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy