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

arXiv: https://arxiv.org/abs/2603.09843 · HTML: https://mlsanity.com/paper/2603.09843/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in LLM reasoning for recommendation, one of 17 directions in LLM reasoning.
- Builds on 2 of its 39 references that are in the map.
- First posted on arXiv 10 Mar 2026.

## Placed in

- LLM reasoning / [LLM reasoning for recommendation](https://mlsanity.com/lr/llm-reasoning-for-recommendation/)
- LLM agents and tool use / [Agentic recommender systems](https://mlsanity.com/agents/agentic-recommender-systems/)

## Builds on (most cited first, 2 of 2)

- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Reason-to-Recommend: Using Interaction-of-Thought Reasoning to Enhance LLM Recommendation](https://mlsanity.com/paper/2506.05069/) (2025)

## Built on by (most cited first, 8 of 8)

- [TSQAgent: Rating Time Series Data Quality via Dedicated Agentic Reasoning](https://mlsanity.com/paper/2606.03629/) (2026)
- [Learning from Online User Feedback for Shopping Agents](https://mlsanity.com/paper/2608.11604/) (2026)
- [A Taxonomy of Cognitive Capability Gaps in Generative and Agentic AI](https://mlsanity.com/paper/2608.02553/) (2026)
- [AtomRec: Evolving Atomic Memory for Agentic Recommendation](https://mlsanity.com/paper/2609.04882/) (2026)
- [RecToolBench: Benchmarking Recommendation-Specific Tool Orchestration under Fuzzy User Intent](https://mlsanity.com/paper/2609.30717/) (2026)
- [AgentRecommender: LLM Agents Enable Customizable Recommender Systems on the User Side](https://mlsanity.com/paper/2609.31166/) (2026)
- [RealWorldShop: Benchmarking and Improving Conversational Shopping Agents in Real-World E-commerce](https://mlsanity.com/paper/2609.38974/) (2026)
- [Personal-Agent Mediated Recommendation with Cross-Platform User History](https://mlsanity.com/paper/2610.07588/) (2026)

## Abstract (arXiv)

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.