# Question-to-Knowledge (Q2K): Multi-Agent Generation of Inspectable Facts for Product Mapping

arXiv: https://arxiv.org/abs/2509.01182 · HTML: https://mlsanity.com/paper/2509.01182/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 24 references that are in the map.
- First posted on arXiv 1 Sep 2025.

## Builds on (most cited first, 18 of 18)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Automatic Prompt Optimization with "Gradient Descent" and Beam Search](https://mlsanity.com/paper/2305.03495/) (2023)
- [Query2doc: Query Expansion with Large Language Models](https://mlsanity.com/paper/2303.07678/) (2023)
- [Does Prompt Formatting Have Any Impact on LLM Performance?](https://mlsanity.com/paper/2411.10541/) (2024)
- [What Did I Do Wrong? Quantifying LLMs' Sensitivity and Consistency to Prompt Engineering](https://mlsanity.com/paper/2406.12334/) (2024)
- [MILL: Mutual Verification with Large Language Models for Zero-Shot Query Expansion](https://mlsanity.com/paper/2310.19056/) (2023)
- [Query Rewriting via Cycle-Consistent Translation for E-Commerce Search](https://mlsanity.com/paper/2103.00800/) (2021)
- [Can Generative LLMs Create Query Variants for Test Collections? An Exploratory Study](https://mlsanity.com/paper/2501.17981/) (2025)
- [PUMGPT: A Large Vision-Language Model for Product Understanding](https://mlsanity.com/paper/2308.09568/) (2023)
- [Multi-Modal Attribute Extraction for E-Commerce](https://mlsanity.com/paper/2203.03441/) (2022)
- [Learning variant product relationship and variation attributes from e-commerce website structures](https://mlsanity.com/paper/2410.02779/) (2024)
- [ProMap: Datasets for Product Mapping in E-commerce](https://mlsanity.com/paper/2309.06882/) (2023)
- [A Multi-Agent Perspective on Modern Information Retrieval](https://mlsanity.com/paper/2502.14796/) (2025)
- [Searching, fast and slow, through product catalogs](https://mlsanity.com/paper/2401.00737/) (2024)
- [AIAP: A No-Code Workflow Builder for Non-Experts with Natural Language and Multi-Agent Collaboration](https://mlsanity.com/paper/2508.02470/) (2025)

## Built on by (most cited first, 2 of 2)

- [RoTRAG: Rule of Thumb Reasoning for Conversation Harm Detection with Retrieval-Augmented Generation](https://mlsanity.com/paper/2604.17301/) (2026)
- [EPM-RL: Reinforcement Learning for On-Premise Product Mapping in E-Commerce](https://mlsanity.com/paper/2604.23993/) (2026)

## Abstract (arXiv)

Identifying whether two product listings refer to the same Stock Keeping Unit (SKU) is a persistent challenge in ecommerce, especially when explicit identifiers are missing and product names vary widely across platforms. Rule based heuristics and keyword similarity often misclassify products by overlooking subtle distinctions in brand, specification, or bundle configuration. To overcome these limitations, we propose Question to Knowledge (Q2K), a multi agent framework that leverages Large Language Models (LLMs) for reliable SKU mapping. Q2K integrates: (1) a Reasoning Agent that generates targeted disambiguation questions, (2) a Knowledge Agent that resolves them via focused web searches, and (3) a Deduplication Agent that reuses validated reasoning traces to reduce redundancy and ensure consistency. A human in the loop mechanism further refines uncertain cases. Experiments on real world consumer goods datasets show that Q2K surpasses strong baselines, achieving higher accuracy and robustness in difficult scenarios such as bundle identification and brand origin disambiguation. By reusing retrieved reasoning instead of issuing repeated searches, Q2K balances accuracy with efficiency, offering a scalable and interpretable solution for product integration.