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

arXiv: https://arxiv.org/abs/2601.17617 · HTML: https://mlsanity.com/paper/2601.17617/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 16 of its 60 references that are in the map.
- First posted on arXiv 24 Jan 2026.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 16 of 16)

- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset](https://mlsanity.com/paper/2309.11998/) (2023)
- [Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity](https://mlsanity.com/paper/2403.14403/) (2024)
- [WebWalker: Benchmarking LLMs in Web Traversal](https://mlsanity.com/paper/2501.07572/) (2025)
- [Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation](https://mlsanity.com/paper/2409.12941/) (2024)
- [Which Economic Tasks are Performed with AI? Evidence from Millions of Claude Conversations](https://mlsanity.com/paper/2503.04761/) (2025)
- [How Do AI Agents Do Human Work? Comparing AI and Human Workflows Across Diverse Occupations](https://mlsanity.com/paper/2510.22780/) (2025)
- [Human vs. Agent in Task-Oriented Conversations](https://mlsanity.com/paper/2509.17619/) (2025)
- [Psychological and behavioural responses in human-agent vs. human-human interactions: a systematic review and meta-analysis](https://mlsanity.com/paper/2509.21542/) (2025)

## Built on by (most cited first, 4 of 4)

- [Revision or Re-Solving? Decomposing Second-Pass Gains in Multi-LLM Pipelines](https://mlsanity.com/paper/2604.01029/) (2026)
- [Effective Reinforcement Learning for Agentic Search by Recycling Zero-Variance Queries During Training](https://mlsanity.com/paper/2606.10709/) (2026)
- [Same Agent, Different Answers: A Repeat-Aware Audit of Corpus-Induced Answer Churn in Retrieval-Augmented QA](https://mlsanity.com/paper/2608.22856/) (2026)
- [DeepStress: Stress-Testing Deep Search Agents](https://mlsanity.com/paper/2607.13920/) (2026)

## Abstract (arXiv)

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 reflected in later queries. 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 lexically 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, query reformulations are often traceable to retrieved evidence across steps. On average, 54% of newly introduced query terms appear in the accumulated evidence context, with additional traceability to earlier steps beyond the most recent retrieval. These findings provide candidate signals for repetition-aware stopping, intent-adaptive retrieval budgeting, and explicit cross-step context tracking. We released the anonymized logs, making them available at a public HuggingFace~chrefhttps://huggingface.co/datasets/cx-cmu/deepresearchgym-agentic-search-logsrepository.