RecThinker: An Agentic Framework for Tool-Augmented Reasoning in Recommendation

• URL: http://arxiv.org/abs/2603.09843v1
• Date: Tue, 10 Mar 2026 16:07:17 GMT
• Title: RecThinker: An Agentic Framework for Tool-Augmented Reasoning in Recommendation
• Abstract summary: RecThinker is an agentic framework for tool-augmented reasoning in recommendation.<n>We develop a suite of specialized tools for RecThinker, enabling the model to acquire user item-side and collaborative information.
• Score: 63.74915464611075
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) have revolutionized recommendation agents by providing superior reasoning and flexible decision-making capabilities. However, existing methods mainly follow a passive information acquisition paradigm, where agents either rely on static pre-defined workflows or perform reasoning with constrained information. It limits the agent's ability to identify information sufficiency, often leading to suboptimal recommendations when faced with fragmented user profiles or sparse item metadata. To address these limitations, we propose RecThinker, an agentic framework for tool-augmented reasoning in recommendation, which shifts recommendation from passive processing to autonomous investigation by dynamically planning reasoning paths and proactively acquiring essential information via autonomous tool-use. Specifically, RecThinker adopts an Analyze-Plan-Act paradigm, which first analyzes the sufficiency of user-item information and autonomously invokes tool-calling sequences to bridge information gaps between available knowledge and reasoning requirements. We develop a suite of specialized tools for RecThinker, enabling the model to acquire user-side, item-side, and collaborative information for better reasoning and user-item matching. Furthermore, we introduce a self-augmented training pipeline, comprising a Supervised Fine-Tuning (SFT) stage to internalize high-quality reasoning trajectories and a Reinforcement Learning (RL) stage to optimize for decision accuracy and tool-use efficiency. Extensive experiments on multiple benchmark datasets demonstrate that RecThinker consistently outperforms strong baselines in the recommendation scenario.

Related papers

• Personalized Recommendation Tool Learning via Autonomous Language Agents [14.066663148493745]
  We propose an agent-based recommendation framework, memory-based $textbfP$ersonalized $textbfR$ecommendation $textbfT$ool learning via autonomous language $textbfA$gents (PRTA)<n>The agent is responsible for high-level reasoning and personalized tool selection, while traditional recommendation models perform full-ranking scoring.<n>Extensive experiments across three public datasets demonstrate the superiority of modelname over traditional recommendation and LLM-based baselines in improving full-ranking recommendation performance.
  arXiv  Detail & Related papers  (2026-07-22T04:10:41Z)
• Autonomous Information Seeking: A Roadmap for Agentic Recommender Systems [64.88044474617854]
  The rapid integration of large language model-based agents into recommender systems has driven a shift from static, ranking-based pipelines toward autonomous and interactive systems.<n>This survey introduces a unified taxonomy grounded in the level of autonomy and three core paradigms of agentic recommender systems.
  arXiv  Detail & Related papers  (2026-07-05T17:55:05Z)
• Decisive: Guiding User Decisions with Optimal Preference Elicitation from Unstructured Documents [3.7993411952027163]
  We present Decisive, an interactive decision-making framework that combines document-grounded reasoning with Bayesian preference inference.<n>Our approach grounds decisions in an objective option-scoring matrix extracted from source documents, while actively learning a user's latent preference vector through targeted elicitation.<n>Users answer pairwise tradeoff questions adaptively selected to maximize information gain over the final decision.
  arXiv  Detail & Related papers  (2026-04-20T11:42:51Z)
• RecNet: Self-Evolving Preference Propagation for Agentic Recommender Systems [109.9061591263748]
  RecNet is a self-evolving preference propagation framework for recommender systems.<n>It proactively propagates real-time preference updates across related users and items.<n>In the backward phase, the feedback-driven propagation optimization mechanism simulates a multi-agent reinforcement learning framework.
  arXiv  Detail & Related papers  (2026-01-29T12:14:31Z)
• Think before Recommendation: Autonomous Reasoning-enhanced Recommender [25.883091131835172]
  RecZero is a reinforcement learning-based recommendation paradigm that abandons the traditional multi-model and multi-stage distillation approach.<n>The paper explores a hybrid paradigm, RecOne, which combines supervised fine-tuning with RL, initializing the model with cold-start reasoning samples and further optimizing it with RL.
  arXiv  Detail & Related papers  (2025-10-27T07:26:32Z)
• Toward Effective Tool-Integrated Reasoning via Self-Evolved Preference Learning [68.89572566071575]
  Tool-Integrated Reasoning (TIR) enables large language models (LLMs) to improve their internal reasoning ability by integrating external tools.<n>We propose Tool-Light, a framework designed to encourage LLMs to perform TIR efficiently and accurately.<n> Experimental results on 10 datasets demonstrate the effectiveness of Tool-Light.
  arXiv  Detail & Related papers  (2025-09-27T12:53:37Z)
• STARec: An Efficient Agent Framework for Recommender Systems via Autonomous Deliberate Reasoning [54.28691219536054]
  We introduce STARec, a slow-thinking augmented agent framework that endows recommender systems with autonomous deliberative reasoning capabilities.<n>We develop anchored reinforcement training - a two-stage paradigm combining structured knowledge distillation from advanced reasoning models with preference-aligned reward shaping.<n>Experiments on MovieLens 1M and Amazon CDs benchmarks demonstrate that STARec achieves substantial performance gains compared with state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-08-26T08:47:58Z)
• 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)
• Wait, that's not an option: LLMs Robustness with Incorrect Multiple-Choice Options [2.1184929769291294]
  This work introduces a novel framework for evaluating LLMs' capacity to balance instruction-following with critical reasoning.<n>We show that post-training aligned models often default to selecting invalid options, while base models exhibit improved refusal capabilities that scale with model size.<n>We additionally conduct a parallel human study showing similar instruction-following biases, with implications for how these biases may propagate through human feedback datasets used in alignment.
  arXiv  Detail & Related papers  (2024-08-27T19:27:43Z)
• Aligning Explanations for Recommendation with Rating and Feature via Maximizing Mutual Information [29.331050754362803]
  Current explanation generation methods are commonly trained with an objective to mimic existing user reviews. We propose a flexible model-agnostic method named MMI framework to enhance the alignment between the generated natural language explanations and the predicted rating/important item features. Our MMI framework can boost different backbone models, enabling them to outperform existing baselines in terms of alignment with predicted ratings and item features.
  arXiv  Detail & Related papers  (2024-07-18T08:29:55Z)
• Uncertainty-Aware Explainable Recommendation with Large Language Models [15.229417987212631]
  We develop a model that utilizes the ID vectors of user and item inputs as prompts for GPT-2. We employ a joint training mechanism within a multi-task learning framework to optimize both the recommendation task and explanation task. Our method achieves 1.59 DIV, 0.57 USR and 0.41 FCR on the Yelp, TripAdvisor and Amazon dataset respectively.
  arXiv  Detail & Related papers  (2024-01-31T14:06:26Z)
• Time-aware Self-Attention Meets Logic Reasoning in Recommender Systems [0.0]
  We propose a Time-aware Self-Attention with Neural Collaborative Reasoning (TiSANCR) based recommendation model. TiSANCR integrates temporal patterns and self-attention mechanism into reasoning-based recommendation. Experiments on benchmark datasets demonstrate that the proposed TiSANCR achieves significant improvement and consistently outperforms state-of-the-art recommendation methods.
  arXiv  Detail & Related papers  (2022-08-29T01:46:42Z)

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.