Evolving Paradigms in Task-Based Search and Learning: A Comparative Analysis of Traditional Search Engine with LLM-Enhanced Conversational Search System

• URL: http://arxiv.org/abs/2512.00313v1
• Date: Sat, 29 Nov 2025 04:14:14 GMT
• Title: Evolving Paradigms in Task-Based Search and Learning: A Comparative Analysis of Traditional Search Engine with LLM-Enhanced Conversational Search System
• Authors: Zhitong Guan, Yi Wang,
• Abstract summary: Large Language Models (LLMs) are rapidly reshaping information retrieval by enabling interactive, generative, and inference-driven search.<n>This study compares search behavior and learning outcomes in two environments: a standard search engine and an LLM-powered search system.
• Score: 5.956874084659983
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) are rapidly reshaping information retrieval by enabling interactive, generative, and inference-driven search. While traditional keyword-based search remains central to web and academic information access, it often struggles to support multi-step reasoning and exploratory learning tasks. LLM-powered search interfaces, such as ChatGPT and Claude, introduce new capabilities that may influence how users formulate queries, navigate information, and construct knowledge. However, empirical understanding of these effects is still limited. This study compares search behavior and learning outcomes in two environments: a standard search engine and an LLM-powered search system. We investigate (1) how search strategies, query formulation, and evaluation behaviors differ across systems, and (2) how LLM use affects comprehension, knowledge integration, and critical thinking during search-based learning tasks. Findings offer insight into how generative AI shapes information-seeking processes and contribute to ongoing discussions in information retrieval, human-AI interaction, and technology-supported learning.

Related papers

• Reasoning in Action: MCTS-Driven Knowledge Retrieval for Large Language Models [31.859833575765933]
  We introduce a reasoning-aware knowledge retrieval method that enriches large language models with information aligned to the logical structure of conversations.<n>We employ the Monte Carlo Tree Search-inspired search method to effectively navigate through knowledge sentences using common keywords.
  arXiv  Detail & Related papers  (2025-11-28T16:23:54Z)
• DeepMMSearch-R1: Empowering Multimodal LLMs in Multimodal Web Search [61.77858432092777]
  We present DeepMMSearch-R1, the first multimodal large language model capable of performing on-demand, multi-turn web searches.<n>DeepMMSearch-R1 can initiate web searches based on relevant crops of the input image making the image search more effective.<n>We conduct extensive experiments across a range of knowledge-intensive benchmarks to demonstrate the superiority of our approach.
  arXiv  Detail & Related papers  (2025-10-14T17:59:58Z)
• R1-Searcher++: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning [83.256752220849]
  Large Language Models (LLMs) are powerful but prone to hallucinations due to static knowledge.<n>We introduce R1-Searcher++, a framework designed to train LLMs to adaptively leverage both internal and external knowledge sources.<n>Our experiments demonstrate that R1-Searcher++ outperforms previous RAG and reasoning methods and achieves efficient retrieval.
  arXiv  Detail & Related papers  (2025-05-22T17:58:26Z)
• ZeroSearch: Incentivize the Search Capability of LLMs without Searching [69.55482019211597]
  We introduce ZeroSearch, a framework that incentivizes the capabilities of large language models to use a real search engine with simulated searches during training.<n>Our approach begins with lightweight supervised fine-tuning to transform the LLM into a retrieval module capable of generating both useful and noisy documents.
  arXiv  Detail & Related papers  (2025-05-07T17:30:22Z)
• ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning [74.65632662894086]
  We propose ReSearch, a framework that trains LLMs to Reason with Search via reinforcement learning.<n>Our approach treats search operations as integral components of the reasoning chain, where when and how to perform searches is guided by text-based thinking.<n>Analysis reveals that ReSearch naturally elicits advanced reasoning capabilities such as reflection and self-correction.
  arXiv  Detail & Related papers  (2025-03-25T09:00:58Z)
• A Survey of Conversational Search [44.09402706387407]
  We explore the recent advancements and potential future directions in conversational search.<n>We highlight the integration of large language models (LLMs) in enhancing these systems.<n>We provide insights into real-world applications and robust evaluations of current conversational search systems.
  arXiv  Detail & Related papers  (2024-10-21T01:54:46Z)
• Enhancing Exploratory Learning through Exploratory Search with the Emergence of Large Language Models [3.1997856595607024]
  This study attempts to unpack this complexity by combining exploratory search strategies with the theories of exploratory learning.<n>Our work adapts Kolb's learning model by incorporating high-frequency exploration and feedback loops, aiming to promote deep cognitive and higher-order cognitive skill development in students.
  arXiv  Detail & Related papers  (2024-08-09T04:30:16Z)
• When Search Engine Services meet Large Language Models: Visions and Challenges [53.32948540004658]
  This paper conducts an in-depth examination of how integrating Large Language Models with search engines can mutually benefit both technologies. We focus on two main areas: using search engines to improve LLMs (Search4LLM) and enhancing search engine functions using LLMs (LLM4Search)
  arXiv  Detail & Related papers  (2024-06-28T03:52:13Z)
• Large Search Model: Redefining Search Stack in the Era of LLMs [63.503320030117145]
  We introduce a novel conceptual framework called large search model, which redefines the conventional search stack by unifying search tasks with one large language model (LLM) All tasks are formulated as autoregressive text generation problems, allowing for the customization of tasks through the use of natural language prompts. This proposed framework capitalizes on the strong language understanding and reasoning capabilities of LLMs, offering the potential to enhance search result quality while simultaneously simplifying the existing cumbersome search stack.
  arXiv  Detail & Related papers  (2023-10-23T05:52:09Z)
• Synergistic Interplay between Search and Large Language Models for Information Retrieval [141.18083677333848]
  InteR allows RMs to expand knowledge in queries using LLM-generated knowledge collections. InteR achieves overall superior zero-shot retrieval performance compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-05-12T11:58:15Z)
• Boosting Search Engines with Interactive Agents [25.89284695491093]
  This paper presents first steps in designing agents that learn meta-strategies for contextual query refinements. Agents are empowered with simple but effective search operators to exert fine-grained and transparent control over queries and search results.
  arXiv  Detail & Related papers  (2021-09-01T13:11:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.