E-Commerce
Overview
E-commerce research studies how digital marketplaces help buyers find products and sellers manage listings, pricing, advertising, and fulfillment. Common approaches include ranking and recommendation models, contextual bandits, causal and uplift modeling, inventory optimization, and multimodal language models for product understanding and shopping assistance. Systems are evaluated with offline interaction logs, online A/B tests, and interactive storefront benchmarks that test whether agents can complete shopping or business tasks. A central tension is balancing relevance and commercial outcomes with factual grounding, safety, latency, and cost; strong results on short tasks do not yet guarantee reliable long-term agent performance.
Latest papers
73 papers5 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.
SLATE: A Large-Scale Benchmark for Long-Horizon API Selection in E-commerce Tool Use
A Deep Learning Framework for Quantile Demand Forecasting in E-commerce with Doubly Censored Data
RITE: Evaluating End-to-End Resilience to Silent Tool Errors in E-Commerce Agentic Systems
WenSight-Decision-1 for Direct Decisions under E-commerce Rules
GLOBE: Evolving Structured Agentic Memory for E-commerce Product Optimization in Generative Search
Multi-Label Topic Assignment via LLM Distillation: A Comparative Analysis of Generative vs. Discriminative Student Models
From Visual Feedback to Textual Reviews: A Multi-Agent Vision-Language Framework for Image-Grounded Review Assistance
Scaling E-Commerce Attribute Extraction with Parallel Decoding
Positional task conditioning for scalable defect detection across product families in large product catalogs
Visual Search Augmented Chain-of-Thought Reasoning for Attribute Value Extraction from Product Videos
DeepAffinity: Long-Term Aspect Preference Prediction in eCommerce using Small Language Models
Web Price Extraction: State of the Art and an Adaptive Browserless Implementation
The Differential Reasoning Router: Operationalizing Cost-Aware LLM Annotation in E-commerce
How Prolific Sellers Self-Present: Dissecting the Communication Patterns of 1.6 Million Reverb Listings
Designing for the Next Click: Bandits for Real-Time Page Layout
Timing-Aware Repurchase Prediction for Web-Scale E-Commerce: Survival Models for Multi-Surface Grocery Recommendation
Stageboost: Recommending Signals Based on Counterfactual Estimation
Sequential Multimodal Evidence Optimization for Product Media Ranking in E-Commerce
Business Arena: Benchmarking LLM Agents in a Realistic Marketplace
Investigating Artificial Intelligence Digital Sovereignty in Mobile Shopping Apps: A Case Study of Nigeria
MerchantBench: Benchmarking LLM Agents for Long-Term Coherence in E-Commerce Operations
SPARC Segmentation to Prediction via Affine Regression and Counterfactuals
CatalogAgent: A Supervisor-mediated Self-Learning System Enabling Context Engineering for GenAI Models
CatalogAgent, a novel agentic system that continuously improves Generator and Evaluator models for e-commerce catalog enrichment. When disagreements arise from (1) internal conflicts between the LLM-based Generator and Evaluator, or (2) external feedback from sellers on LLM outputs, a Supervisor Agent intervenes to mediate these conflicts and make final decisions. The system also incorporates a Memory Base and a Memory Summarizer that stores Supervisor Agent activities from individual cases and aggregates patterns into learnings. These learnings are fed back to the worker Generator and Evaluator LLMs, enabling self-improvement without human intervention. Through context engineering -- injecting learnings and insights into worker LLMs' contexts -- the system successfully transfers the Supervisor's capabilities to the Generator and Evaluator, improving their performance by 15.24% and 13.98%, respectively. Our experiments demonstrate a new paradigm of Supervisor Agent-mediated self-learning systems for improving generative AI model accuracy.