Related papers: CogSearch: A Cognitive-Aligned Multi-Agent Framewo…
Retrieval-Augmented Generation (RAG) effectively mitigates hallucinations in LLMs by incorporating external knowledge. However, the inherent discrete representation of text in existing frameworks often results in a loss of semantic…
Agentic Web is an emerging paradigm where autonomous agents help users use online information. As the paradigm develops, content providers are also deploying agents to manage their data and serve it through controlled interfaces. This shift…
Agentic retrieval-augmented generation (RAG) systems enable large language models (LLMs) to solve complex tasks through multi-step interaction with external retrieval tools. However, such multi-step interaction often involves redundant…
This paper aims to provide a radical rundown on Conversation Search (ConvSearch), an approach to enhance the information retrieval method where users engage in a dialogue for the information-seeking tasks. In this survey, we predominantly…
Recently, large reasoning models have demonstrated strong mathematical and coding abilities, and deep search leverages their reasoning capabilities in challenging information retrieval tasks. Existing deep search works are generally limited…
The increasing integration of artificial intelligence (AI) in everyday life brings with it new challenges and questions for regarding how humans interact with autonomous agents. Multi-agent experiments, where humans and AI act together, can…
Current search agents fundamentally lack the ability to simultaneously perform \textit{deep} reasoning over multi-hop retrieval and \textit{wide}-scale information collection-a critical deficiency for real-world applications like…
Cognitive agent abstractions can help to engineer intelligent systems across mobile devices. On smartphones, the data obtained from onboard sensors can give valuable insights into the user's current situation. Unfortunately, today's…
Many people browse online communities to learn from others' experiences and opinions, e.g., for constructing travel plans. Conversational search powered by large language models (LLMs) could ease this information-seeking task, but it…
Nowadays, E-commerce is increasingly integrated into our daily lives. Meanwhile, shopping process has also changed incrementally from one behavior (purchase) to multiple behaviors (such as view, carting and purchase). Therefore, utilizing…
Large language models (LLMs) have shown strong potential in recommendation tasks due to their strengths in language understanding, reasoning and knowledge integration. These capabilities are especially beneficial for review-based…
The evolution of Large Language Models (LLMs) has significantly advanced multi-turn conversation systems, emphasizing the need for proactive guidance to enhance users' interactions. However, these systems face challenges in dynamically…
Web is often used for finding information and with a learning intention. In this thesis, we propose a study to investigate the process of learning online across varying cognitive learning levels using crowd-sourced participants. Our aim was…
Selecting the right compiler optimisations has a severe impact on programs' performance. Still, the available optimisations keep increasing, and their effect depends on the specific program, making the task human intractable. Researchers…
With the rise of large language models (LLMs), generative engines are becoming powerful alternatives to traditional search, reshaping retrieval tasks. In e-commerce, for instance, conversational shopping agents now guide consumers to…
In this paper, we investigate the task of aggregating search results from heterogeneous sources in an E-commerce environment. First, unlike traditional aggregated web search that merely presents multi-sourced results in the first page, this…
Traditional e-commerce search systems often struggle with the semantic gap between user queries and product catalogs. In this paper, we propose a Category-Aligned Retrieval System (CARS) that improves search relevance by first predicting…
Deep neural networks have shown promise in collaborative filtering (CF). However, existing neural approaches are either user-based or item-based, which cannot leverage all the underlying information explicitly. We propose CF-UIcA, a neural…
Deep search agents powered by large language models have demonstrated strong capabilities in multi-step retrieval, reasoning, and long-horizon task execution. However, their practical failures often stem from the lack of mechanisms to…
Product retrieval is the backbone of e-commerce search: for each user query, it identifies a high-recall candidate set from billions of items, laying the foundation for high-quality ranking and user experience. Despite extensive…