Related papers: Beyond Retrieval-Ranking: A Multi-Agent Cognitive …

Multilingual e-commerce search suffers from severe data imbalance across languages, label noise, and limited supervision for low-resource languages--challenges that impede the cross-lingual generalization of relevance models despite the…

The rapid adoption of LLM-based agentic systems has produced a rich ecosystem of frameworks (smolagents, LangGraph, AutoGen, CAMEL, LlamaIndex, i.a.). Yet existing benchmarks are model-centric: they fix the agentic setup and do not compare…

Modern retrieval systems do not rely on a single ranking model to construct their rankings. Instead, they generally take a cascading approach where a sequence of ranking models are applied in multiple re-ranking stages. Thereby, they…

Multi-agent systems of large language models (LLMs) show promise for complex reasoning, but their effectiveness is often limited by fixed collaboration protocols. These frameworks typically focus on macro-level orchestration while…

Evaluating retrieval-ranking systems is crucial for developing high-performing models. While online A/B testing is the gold standard, its high cost and risks to user experience require effective offline methods. However, relying on…

Modern e-commerce search is evolving to resolve complex user intents. While Large Language Models (LLMs) offer strong reasoning, existing LLM-based paradigms face a fundamental blindness-latency dilemma: query rewriting is agnostic to…

Conventional methods for query autocompletion aim to predict which completed query a user will select from a list. A shortcoming of this approach is that users often do not know which query will provide the best retrieval performance on the…

In e-commerce, head queries account for the vast majority of gross merchandise sales and improvements to head queries are highly impactful to the business. While most supervised approaches to search perform better in head queries vs. tail…

Recent advances in large language models (LLMs) enabled the development of AI agents that can plan and interact with tools to complete complex tasks. However, literature on their reliability in real-world applications remains limited. In…

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…

Existing item-based collaborative filtering (ICF) methods leverage only the relation of collaborative similarity. Nevertheless, there exist multiple relations between items in real-world scenarios. Distinct from the collaborative similarity…

We study two state-of-the-art solutions to the multi-agent pickup and delivery (MAPD) problem based on different principles -- multi-agent path-finding (MAPF) and multi-agent reinforcement learning (MARL). Specifically, a recent MAPF…

Agentic search -- the task of training agents that iteratively reason, issue queries, and synthesize retrieved information to answer complex questions -- has achieved remarkable progress through reinforcement learning (RL). However,…

Real-time bidding (RTB) plays a pivotal role in online advertising ecosystems. Advertisers employ strategic bidding to optimize their advertising impact while adhering to various financial constraints, such as the return-on-investment (ROI)…

Finding near-optimal solutions for dense multi-agent pathfinding (MAPF) problems in real-time remains challenging even for state-of-the-art planners. To this end, we develop a hybrid framework that integrates a learned heuristic derived…

Large language models (LLMs) have achieved impressive results in natural language understanding, yet their reasoning capabilities remain limited when operating as single agents. Multi-Agent Debate (MAD) has been proposed to address this…

Implicit Attribute Value Extraction (AVE) is essential for accurately representing products in e-commerce, as it infers latent attributes from multimodal data. Despite advances in multimodal large language models (MLLMs), implicit AVE…

Large language model (LLM)-based agents are increasingly used to perform complex, multi-step workflows in regulated settings such as compliance and due diligence. However, many agentic architectures rely primarily on prompt engineering of a…

Multi-Agent Path Finding (MAPF) is a fundamental problem in artificial intelligence and robotics, requiring the computation of collision-free paths for multiple agents navigating from their start locations to designated goals. As autonomous…

Large transformer models, trained on diverse datasets, have demonstrated impressive few-shot performance on previously unseen tasks without requiring parameter updates. This capability has also been explored in Reinforcement Learning (RL),…