In this article, we study the problem of dynamic personalized product search. Due to the data-sparsity problem in the real world, existing methods suffer from the challenge of data inefficiency. We address the challenge by proposing a Dynamic Bayesian Contrastive Predictive Coding model (DBCPC), which aims to capture the rich structured information behind search records to improve data efficiency. Our proposed DBCPC utilizes contrastive predictive learning to jointly learn dynamic embeddings with structure information of entities (i.e., users, products, and words). Specifically, our DBCPC employs structured prediction to tackle the intractability caused by non-linear output space and utilizes the time embedding technique to avoid designing different encoders each time in the Dynamic Bayesian models. In this way, our model jointly learns the underlying embeddings of entities (i.e., users, products, and words) via prediction tasks, which enables the embeddings to focus more on their general attributes and capture the general information during the preference evolution with time. For inferring the dynamic embeddings, we propose an inference algorithm combining the variational objective and the contrastive objectives. Experiments were conducted on an Amazon dataset and the experimental results show that our proposed DBCPC can learn the higher-quality embeddings and outperforms the state-of-the-art non-dynamic and dynamic models for product search.

As AI agents and tools increasingly carry out everyday tasks on behalf of users, the digital ecosystem is rapidly filling with agents that offer overlapping or complementary functionalities, raising a fundamental challenge: how can users, developers, and orchestrating systems effectively identify, compare, and select the most appropriate agents or tools for a given task? While rooted in traditional information retrieval (IR), agent search introduces new challenges because the retrieved entities are executable systems rather than static information artifacts, and their suitability depends on capabilities, behaviors, constraints, uncertainty, and task-dependent performance. We argue that the IR community is well-positioned to advance this emerging problem setting, which we refer to as AgentSearch, by developing principled methods for representing, indexing, retrieving, and ranking AI agents and tools under multi-dimensional relevance criteria. The AgentSearch Workshop aims to bring together researchers and practitioners from academia and industry to explore the challenges and opportunities of agent and tool search, including agent discovery, capability representation, retrieval and ranking models, evaluation methodologies, and issues related to safety, fairness, personalization, and explainability. To support concrete progress, the workshop will also host an exploratory AgentSearch Challenge that provides a shared experimental setting for ranking agents given a task. The workshop will adopt an interactive format featuring breakout discussions, poster and spotlight sessions, invited talks, and collaborative activities, fostering active engagement and cross-disciplinary exchange beyond a traditional mini-conference structure.

AI agents and tools are increasingly moving beyond passive information processing toward executable systems that can perceive inputs, reason over intermediate states, call external tools, interact with environments, and complete user-specified tasks. As coding agents, deep research agents, workflow automation systems, and multi-agent platforms continue to proliferate, users and orchestrating systems face a growing challenge: how to identify, compare, and select suitable agents or tools from large, heterogeneous, and evolving candidate spaces. This emerging problem, which we refer to as agent and tool search, differs from traditional information retrieval because the search targets are not static information artifacts, but executable systems whose relevance depends on capability, competence, reliability, safety, cost, and downstream task performance. In this survey, we provide a systematic overview of agent and tool search. We characterize agent search as a retrieval and decision-making problem over executable systems and organize existing work along an end-to-end pipeline covering task understanding, representation, indexing, retrieval, reranking, selection, and evaluation. We further discuss system-level dimensions, representative applications, and open challenges in capability modeling, uncertainty handling, relevance definition, and evaluation protocol design. By synthesizing fragmented work across information retrieval, multi-agent systems, tool learning, agent evaluation, and AI systems design, this survey aims to provide a coherent foundation for future research on agent and tool search.