Agentic Search in the Wild: Intents and Trajectory Dynamics from 14M+ Real Search Requests

• URL: http://arxiv.org/abs/2601.17617v1
• Date: Sat, 24 Jan 2026 22:42:43 GMT
• Title: Agentic Search in the Wild: Intents and Trajectory Dynamics from 14M+ Real Search Requests
• Authors: Jingjie Ning, João Coelho, Yibo Kong, Yunfan Long, Bruno Martins, João Magalhães, Jamie Callan, Chenyan Xiong,
• Abstract summary: This paper presents a large-scale log analysis of agentic search based on 14.44M search requests (3.97M sessions) collected from DeepResearch.<n>Our analyses reveal distinctive behavioral patterns. First, over 90% of multi-turn sessions contain at most ten steps, and 89% of inter-step intervals fall under one minute.<n>Findings suggest that agentic search may benefit from repetition-aware early stopping, intent-adaptive retrieval budgets, and explicit cross-step context tracking.
• Score: 28.788329427390455
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: LLM-powered search agents are increasingly being used for multi-step information seeking tasks, yet the IR community lacks empirical understanding of how agentic search sessions unfold and how retrieved evidence is used. This paper presents a large-scale log analysis of agentic search based on 14.44M search requests (3.97M sessions) collected from DeepResearchGym, i.e. an open-source search API accessed by external agentic clients. We sessionize the logs, assign session-level intents and step-wise query-reformulation labels using LLM-based annotation, and propose Context-driven Term Adoption Rate (CTAR) to quantify whether newly introduced query terms are traceable to previously retrieved evidence. Our analyses reveal distinctive behavioral patterns. First, over 90% of multi-turn sessions contain at most ten steps, and 89% of inter-step intervals fall under one minute. Second, behavior varies by intent. Fact-seeking sessions exhibit high repetition that increases over time, while sessions requiring reasoning sustain broader exploration. Third, agents reuse evidence across steps. On average, 54% of newly introduced query terms appear in the accumulated evidence context, with contributions from earlier steps beyond the most recent retrieval. The findings suggest that agentic search may benefit from repetition-aware early stopping, intent-adaptive retrieval budgets, and explicit cross-step context tracking. We plan to release the anonymized logs to support future research.

Related papers

• Revisiting Text Ranking in Deep Research [24.324221566628125]
  Black-box web search APIs hinder systematic analysis of search components.<n>We reproduce a selection of key findings and best practices for IR text ranking methods in the deep research setting.
  arXiv  Detail & Related papers  (2026-02-25T00:18:07Z)
• Over-Searching in Search-Augmented Large Language Models [22.821710825732563]
  Search-augmented large language models (LLMs) excel at knowledge-intensive tasks by integrating external retrieval.<n>Over-searching leads to computational inefficiency and hallucinations by incorporating irrelevant context.<n>Our finding shows: (i) search generally improves answer accuracy on answerable queries but harms abstention on unanswerable ones; (ii) over-searching is more pronounced in complex reasoning models and deep research systems; and (iii) the composition of retrieved evidence is crucial, as the presence of negative evidence improves abstention.
  arXiv  Detail & Related papers  (2026-01-09T03:24:46Z)
• Beyond the limitation of a single query: Train your LLM for query expansion with Reinforcement Learning [23.104182075898297]
  Reasoning-augmented search agents, such as Search-R1, are trained to reason, search, and generate the final answer iteratively.<n>We train an LLM-based search agent with the native capability of query expansion through reinforcement learning.<n>With the assistance of the squeezer model, we discover that even a small-scale 3B LLM can demonstrate a strong capability of query expansion.
  arXiv  Detail & Related papers  (2025-10-11T04:23:30Z)
• Reasoning-enhanced Query Understanding through Decomposition and Interpretation [87.56450566014625]
  ReDI is a Reasoning-enhanced approach for query understanding through Decomposition and Interpretation.<n>We compiled a large-scale dataset of real-world complex queries from a major search engine.<n> Experiments on BRIGHT and BEIR demonstrate that ReDI consistently surpasses strong baselines in both sparse and dense retrieval paradigms.
  arXiv  Detail & Related papers  (2025-09-08T10:58:42Z)
• MMSearch-R1: Incentivizing LMMs to Search [49.889749277236376]
  We present MMSearch-R1, the first end-to-end reinforcement learning framework that enables on-demand, multi-turn search in real-world Internet environments.<n>Our framework integrates both image and text search tools, allowing the model to reason about when and how to invoke them guided by an outcome-based reward with a search penalty.
  arXiv  Detail & Related papers  (2025-06-25T17:59:42Z)
• Query-oriented Data Augmentation for Session Search [71.84678750612754]
  We propose query-oriented data augmentation to enrich search logs and empower the modeling. We generate supplemental training pairs by altering the most important part of a search context. We develop several strategies to alter the current query, resulting in new training data with varying degrees of difficulty.
  arXiv  Detail & Related papers  (2024-07-04T08:08:33Z)
• LightPAL: Lightweight Passage Retrieval for Open Domain Multi-Document Summarization [9.739781953744606]
  Open-Domain Multi-Document Summarization (ODMDS) is the task of generating summaries from large document collections in response to user queries. Traditional retrieve-then-summarize approaches fall short for open-ended queries in ODMDS tasks. We propose LightPAL, a lightweight passage retrieval method for ODMDS.
  arXiv  Detail & Related papers  (2024-06-18T10:57:27Z)
• Lexically-Accelerated Dense Retrieval [29.327878974130055]
  'LADR' (Lexically-Accelerated Dense Retrieval) is a simple-yet-effective approach that improves the efficiency of existing dense retrieval models. LADR consistently achieves both precision and recall that are on par with an exhaustive search on standard benchmarks.
  arXiv  Detail & Related papers  (2023-07-31T15:44:26Z)
• Graph Enhanced BERT for Query Understanding [55.90334539898102]
  query understanding plays a key role in exploring users' search intents and facilitating users to locate their most desired information. In recent years, pre-trained language models (PLMs) have advanced various natural language processing tasks. We propose a novel graph-enhanced pre-training framework, GE-BERT, which can leverage both query content and the query graph.
  arXiv  Detail & Related papers  (2022-04-03T16:50:30Z)
• Exposing Query Identification for Search Transparency [69.06545074617685]
  We explore the feasibility of approximate exposing query identification (EQI) as a retrieval task by reversing the role of queries and documents in two classes of search systems. We derive an evaluation metric to measure the quality of a ranking of exposing queries, as well as conducting an empirical analysis focusing on various practical aspects of approximate EQI.
  arXiv  Detail & Related papers  (2021-10-14T20:19:27Z)
• Session-Aware Query Auto-completion using Extreme Multi-label Ranking [61.753713147852125]
  We take the novel approach of modeling session-aware query auto-completion as an e Multi-Xtreme Ranking (XMR) problem. We adapt a popular XMR algorithm for this purpose by proposing several modifications to the key steps in the algorithm. Our approach meets the stringent latency requirements for auto-complete systems while leveraging session information in making suggestions.
  arXiv  Detail & Related papers  (2020-12-09T17:56:22Z)

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.