ReasonRec: A Reasoning-Augmented Multimodal Agent for Unified Recommendation

• URL: http://arxiv.org/abs/2606.28357v1
• Date: Mon, 08 Jun 2026 22:40:35 GMT
• Title: ReasonRec: A Reasoning-Augmented Multimodal Agent for Unified Recommendation
• Abstract summary: ReasonRec is a reasoning-augmented multimodal agent structured around a three-stage explicit reasoning pipeline.<n>We show that ReasonRec achieves over 30% relative improvement in key ranking metrics compared to state-of-the-art multimodal recommenders.
• Score: 51.238500135659656
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in multimodal recommenders excel at feature fusion but remain opaque and inefficient decision-makers, lacking explicit reasoning and self-awareness of uncertainty. We introduce ReasonRec, a reasoning-augmented multimodal agent structured around a three-stage explicit reasoning pipeline. Specifically, we propose a reasoning-aware visual instruction tuning strategy that systematically transforms diverse recommendation tasks into unified CoT prompts, enabling the VLM to explicitly articulate intermediate decision steps. Additionally, our evidence-horizon curriculum progressively enhances the reasoning complexity to better handle cold-start and long-tail user scenarios, significantly boosting model generalization. Furthermore, the uncertainty-guided delegation mechanism empowers the agent to assess its own confidence, strategically allocating computational resources to optimize both recommendation accuracy and inference efficiency. Comprehensive experiments on four standard recommendation tasks across five real-world datasets demonstrate that ReasonRec achieves over 30% relative improvement in key ranking metrics compared to state-of-the-art multimodal recommenders. Crucially, ReasonRec substantially reduces inference latency by dynamically delegating up to 35% of queries to efficient sub-models without compromising accuracy. Extensive ablation studies further confirm that each proposed reasoning and planning mechanism individually contributes substantially to ReasonRec's overall effectiveness. Collectively, our results illustrate a clear pathway towards interpretable, adaptive, and efficient multimodal recommendation through explicit reasoning and agentic design.

Related papers

• WhisperRec: Latent Reasoning for Efficient Foundation Recommendation Models [51.88075626243057]
  We propose WhisperRec, an efficient latent reasoning framework for foundation recommendation models (FRMs)<n>WhisperRec compresses teacher-generated Chain-of-Thought (CoT) into learnable latent reasoning tokens.<n>We show that WhisperRec consistently outperforms explicit-CoT methods and conventional baselines.
  arXiv  Detail & Related papers  (2026-07-29T08:48:35Z)
• Reinforced Preference Optimization for Reasoning-Augmented Recommendations [34.99578717556569]
  We introduce RPORec, a reinforced preference optimization framework for Recommender systems.<n>RPORec unifies an LLM backbone's reasoning ability with a dedicated recommendation head (Rechead) for precise item retrieval.<n>Extensive experiments on public benchmarks and large-scale online deployments show that RPORec consistently outperforms state-of-the-art LLM-based recommendation methods.
  arXiv  Detail & Related papers  (2026-05-21T03:56:42Z)
• Verifiable Reasoning for LLM-based Generative Recommendation [106.7765000777685]
  Reasoning in Large Language Models (LLMs) has recently shown strong potential in enhancing generative recommendation.<n>We propose a novel textbftextitreason-verify-recommend paradigm, which interleaves reasoning with verification to provide reliable feedback.<n>Experiments on four real-world datasets demonstrate that VRec substantially enhances recommendation effectiveness and scalability without compromising efficiency.
  arXiv  Detail & Related papers  (2026-03-08T16:55:45Z)
• DTRec: Learning Dynamic Reasoning Trajectories for Sequential Recommendation [19.181171482637513]
  We propose DTRec, a novel and effective framework that explores the Dynamic reasoning Trajectory for Sequential Recommendation along both direction and depth.<n>To guide the direction, we develop Hierarchical Process Supervision (HPS), which provides coarse-to-fine supervisory signals to emulate the natural, progressive refinement of human cognitive processes.<n>To optimize the depth, we introduce the Adaptive Reasoning Halting (ARH) mechanism that dynamically adjusts the number of reasoning steps by jointly monitoring three indicators.
  arXiv  Detail & Related papers  (2025-12-16T03:04:43Z)
• OneRec-Think: In-Text Reasoning for Generative Recommendation [55.53292983432484]
  OneRec-Think is a unified framework that seamlessly integrates dialogue, reasoning, and personalized recommendation.<n>Our proposed "Think-Ahead" architecture enables effective industrial deployment on Kuaishou, achieving a 0.159% gain in APP Stay Time.
  arXiv  Detail & Related papers  (2025-10-13T17:20:13Z)
• REG4Rec: Reasoning-Enhanced Generative Model for Large-Scale Recommendation Systems [25.59169452367297]
  Sequential recommendation aims to predict a user's next action in large-scale recommender systems.<n>Recent studies have introduced a reasoning process into generative recommendation, significantly improving recommendation performance.<n>These approaches are constrained by the singularity of item semantic representations.<n>We introduce REG4Rec, a reasoning-enhanced generative model that constructs multiple dynamic semantic reasoning paths.
  arXiv  Detail & Related papers  (2025-08-21T07:02:51Z)
• Don't Think Longer, Think Wisely: Optimizing Thinking Dynamics for Large Reasoning Models [68.96619605651155]
  Large reasoning models (LRMs) may drastically increase the output length due to overthinking.<n>We propose a dynamic optimization framework that segments model-generated reasoning paths into distinct thinking patterns.<n>Our method achieves up to a 12% accuracy improvement and reducing token usage from approximately 5,000 to 3,000 tokens.
  arXiv  Detail & Related papers  (2025-05-27T20:59:29Z)
• Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuning [31.727984223052648]
  This paper proposes UnifiedReward-Think, the first unified multimodal CoT-based reward model.<n>We first use a small amount of image generation preference data to distill the reasoning process of GPT-4o.<n>We then prepare large-scale unified multimodal preference data to elicit the model's reasoning process across various vision tasks.
  arXiv  Detail & Related papers  (2025-05-06T08:46:41Z)
• On the Role of Feedback in Test-Time Scaling of Agentic AI Workflows [71.92083784393418]
  Agentic AI (systems that autonomously plan and act) are becoming widespread, yet their task success rate on complex tasks remains low.<n>Inference-time alignment relies on three components: sampling, evaluation, and feedback.<n>We introduce Iterative Agent Decoding (IAD), a procedure that repeatedly inserts feedback extracted from different forms of critiques.
  arXiv  Detail & Related papers  (2025-04-02T17:40:47Z)
• Reason4Rec: Large Language Models for Recommendation with Deliberative User Preference Alignment [69.11529841118671]
  We propose a new Deliberative Recommendation task, which incorporates explicit reasoning about user preferences as an additional alignment goal.<n>We then introduce the Reasoning-powered Recommender framework for deliberative user preference alignment.
  arXiv  Detail & Related papers  (2025-02-04T07:17:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.