Related papers: FitText: Evolving Agent Tool Ecologies via Memetic…

This article aims to provide the information retrieval community with some reflections on recent advances in retrieval learning by analyzing the reproducibility of image-text retrieval models. Due to the increase of multimodal data over the…

Retrieval-Augmented Generation (RAG) enhances language models by incorporating external knowledge at inference time. However, graph-based RAG systems often suffer from structural overhead and imprecise retrieval: they require costly…

Generative retrieval introduces a groundbreaking paradigm to document retrieval by directly generating the identifier of a pertinent document in response to a specific query. This paradigm has demonstrated considerable benefits and…

Recent work explores agentic inference-time techniques to perform structured, multi-step reasoning. However, stateless inference often struggles on multi-step tasks due to the absence of persistent state. Moreover, task-specific fine-tuning…

Existing AI-generated text detection methods heavily depend on large annotated datasets and external threshold tuning, restricting interpretability, adaptability, and zero-shot effectiveness. To address these limitations, we propose…

Open-domain multimodal document retrieval aims to retrieve specific components (paragraphs, tables, or images) from large and interconnected document corpora. Existing graph-based retrieval approaches typically rely on a uniform similarity…

Information retrieval (IR) systems have traditionally been designed and trained for human users, with learning-to-rank methods relying heavily on large-scale human interaction logs such as clicks and dwell time. With the rapid emergence of…

Retrieval-Augmented Generation (RAG) couples a retriever with a large language model (LLM) to ground generated responses in external evidence. While this framework enhances factuality and domain adaptability, it faces a key bottleneck:…

Today's algorithm-driven interfaces, from recommendation feeds to GenAI tools, often prioritize engagement and efficiency at the expense of user agency. As systems take on more decision-making, users have less control over what they see and…

In agent memory systems, the reranking model serves as the critical bridge connecting user queries with long-term memory. Most systems adopt the "retrieve-then-rerank" two-stage paradigm, but generic reranking models rely on semantic…

Innovation in Recommender Systems is currently impeded by a fractured ecosystem, where researchers must choose between the ease of in-memory experimentation and the costly, complex rewriting required for distributed industrial engines. To…

Agentic evolution has emerged as a powerful paradigm for improving programs, workflows, and scientific solutions by iteratively generating candidates, evaluating them, and using feedback to guide future search. However, existing methods are…

Large Reasoning Models (LRMs) like o3 and DeepSeek-R1 have achieved remarkable progress in reasoning tasks with long cot. However, they remain computationally inefficient and struggle with accuracy when solving problems requiring complex…

This technical report details a novel approach to combining reasoning and retrieval augmented generation (RAG) within a single, lean language model architecture. While existing RAG systems typically rely on large-scale models and external…

Automatic Term Extraction (ATE) identifies domain-specific expressions that are crucial for downstream tasks such as machine translation and information retrieval. Although large language models (LLMs) have significantly advanced various…

Recent advances in language model (LM) agents and function calling have enabled autonomous, feedback-driven systems to solve problems across various digital domains. To better understand the unique limitations of LM agents, we introduce…

Large language models (LLMs) have the remarkable ability to solve new tasks with just a few examples, but they need access to the right tools. Retrieval Augmented Generation (RAG) addresses this problem by retrieving a list of relevant…

Modern recruitment platforms operate under severe information imbalance: job seekers must search over massive, rapidly changing collections of postings, while employers are overwhelmed by high-volume, low-relevance applicant pools. Existing…

Recent advances in large language models have enabled the development of viable generative retrieval systems. Instead of a traditional document ranking, generative retrieval systems often directly return a grounded generated text as a…

Agentic systems, AI architectures that autonomously execute multi-step workflows to achieve complex goals, are often built using repeated large language model (LLM) calls for closed-set decision tasks such as routing, shortlisting, gating,…