Related papers: SmartSearch: Process Reward-Guided Query Refinemen…

Semantic search with large language models (LLMs) enables retrieval by meaning rather than keyword overlap, but scaling it requires major inference efficiency advances. We present LinkedIn's LLM-based semantic search framework for AI Job…

Despite the recent advancement in Retrieval-Augmented Generation (RAG) systems, most retrieval methodologies are often developed for factual retrieval, which assumes query and positive documents are semantically similar. In this paper, we…

This paper presents first successful steps in designing search agents that learn meta-strategies for iterative query refinement in information-seeking tasks. Our approach uses machine reading to guide the selection of refinement terms from…

Retrieval-Augmented Generation (RAG) enables large language models (LLMs) to access external knowledge sources, but the effectiveness of RAG relies on the coordination between the retriever and the generator. Since these components are…

Large language models (LLMs) are incredible and versatile tools for text-based tasks that have enabled countless, previously unimaginable, applications. Retrieval models, in contrast, have not yet seen such capable general-purpose models…

Recent advancements in Large Language Models(LLMs) have demonstrated their capabilities not only in reasoning but also in invoking external tools, particularly search engines. However, teaching models to discern when to invoke search and…

Search agents powered by large language models can autonomously decompose queries, retrieve information, and synthesize answers through multi-step reasoning. However, the rapid growth of training methods has outpaced controlled comparison:…

Retrieval-augmented generation (RAG) enhances the text generation capabilities of large language models (LLMs) by integrating external knowledge and up-to-date information. However, traditional RAG systems are limited by static workflows…

Streaming services have reshaped how we discover and engage with digital entertainment. Despite these advancements, effectively understanding the wide spectrum of user search queries continues to pose a significant challenge. An accurate…

Systematic reviews require the use of rigorously designed search strategies to ensure both comprehensive retrieval and minimization of bias. Conventional manual approaches, although methodologically systematic, are resource-intensive and…

Effective decision-making in Large Language Models (LLMs) is essential for handling intricate tasks. However, existing approaches prioritize performance but often overlook the balance between effectiveness and computational cost. To address…

Equipping large language models (LLMs) with search engines via reinforcement learning (RL) has emerged as an effective approach for building search agents. However, overreliance on search introduces unnecessary cost and risks exposure to…

Recent advancements in Large Language Models (LLMs) have led to significant breakthroughs in various natural language processing tasks. However, generating factually consistent responses in knowledge-intensive scenarios remains a challenge…

Recent years have seen considerable advancements in multi-step reasoning with Large Language Models (LLMs). The previous studies have elucidated the merits of integrating feedback or search mechanisms during model inference to improve the…

Large language models (LLMs) have demonstrated remarkable capabilities across a range of text-generation tasks. However, LLMs still struggle with problems requiring multi-step decision-making and environmental feedback, such as online…

Recent deep research agents primarily improve performance by scaling reasoning depth, but this leads to high inference cost and latency in search-intensive scenarios. Moreover, generalization across heterogeneous research settings remains…

Information retrieval systems are crucial for enabling effective access to large document collections. Recent approaches have leveraged Large Language Models (LLMs) to enhance retrieval performance through query augmentation, but often rely…

Large Language Models (LLMs) are prone to hallucination, especially during multi-hop and reasoning-intensive tasks such as mathematical problem solving. While Outcome Reward Models verify only final answers, Process Reward Models (PRMs)…

Reward-guided search methods have demonstrated strong potential in enhancing tool-using agents by effectively guiding sampling and exploration over complex action spaces. As a core design, those search methods utilize process reward models…

While Large Language Models (LLMs) achieve near-human performance on standard benchmarks, their capabilities often fail to generalize to complex, real-world problems. To bridge this gap, we introduce DeepQuestion, a scalable, automated…