# USimAgent: Large Language Models for Simulating Search Users

arXiv: https://arxiv.org/abs/2403.09142 · HTML: https://mlsanity.com/paper/2403.09142/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 40 references that are in the map.
- First posted on arXiv 14 Mar 2024.

## Builds on (most cited first, 10 of 10)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [ViperGPT: Visual Inference via Python Execution for Reasoning](https://mlsanity.com/paper/2303.08128/) (2023)
- [MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge](https://mlsanity.com/paper/2206.08853/) (2022)
- [SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks](https://mlsanity.com/paper/2305.17390/) (2023)
- [Generative Query Reformulation for Effective Adhoc Search](https://mlsanity.com/paper/2308.00415/) (2023)

## Built on by (most cited first, 30 of 32)

- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [Collaborative Gym: A Framework for Enabling and Evaluating Human-Agent Collaboration](https://mlsanity.com/paper/2412.15701/) (2024)
- [Mind the Sim2Real Gap in User Simulation for Agentic Tasks](https://mlsanity.com/paper/2603.11245/) (2026)
- [From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents](https://mlsanity.com/paper/2506.18959/) (2025)
- [A Survey of Large Language Model Empowered Agents for Recommendation and Search: Towards Next-Generation Information Retrieval](https://mlsanity.com/paper/2503.05659/) (2025)
- [Towards Agentic Recommender Systems in the Era of Multimodal Large Language Models](https://mlsanity.com/paper/2503.16734/) (2025)
- [A Survey of Conversational Search](https://mlsanity.com/paper/2410.15576/) (2024)
- [SABER: Small Actions, Big Errors -- Safeguarding Mutating Steps in LLM Agents](https://mlsanity.com/paper/2512.07850/) (2025)
- [Shop-R1: Rewarding LLMs to Simulate Human Behavior in Online Shopping via Reinforcement Learning](https://mlsanity.com/paper/2507.17842/) (2025)
- [A Survey on LLM-based Conversational User Simulation](https://mlsanity.com/paper/2604.24977/) (2026)
- [A Survey of Foundation Model-Powered Recommender Systems: From Feature-Based, Generative to Agentic Paradigms](https://mlsanity.com/paper/2504.16420/) (2025)
- [ConvApparel: A Benchmark Dataset and Validation Framework for User Simulators in Conversational Recommenders](https://mlsanity.com/paper/2602.16938/) (2026)
- [Conversational Search: From Fundamentals to Frontiers in the LLM Era](https://mlsanity.com/paper/2506.10635/) (2025)
- [MAO-ARAG: Multi-Agent Orchestration for Adaptive Retrieval-Augmented Generation](https://mlsanity.com/paper/2508.01005/) (2025)
- [Lusifer: LLM-based User SImulated Feedback Environment for online Recommender systems](https://mlsanity.com/paper/2405.13362/) (2024)
- [Apollonion: Profile-centric Dialog Agent](https://mlsanity.com/paper/2404.08692/) (2024)
- [What can large language models do for sustainable food?](https://mlsanity.com/paper/2503.04734/) (2025)
- [Mirroring Users: Towards Building Preference-aligned User Simulator with User Feedback in Recommendation](https://mlsanity.com/paper/2508.18142/) (2025)
- [Reinforcing Human Behavior Simulation via Verbal Feedback](https://mlsanity.com/paper/2605.20506/) (2026)
- [G-UBS: Towards Robust Understanding of Implicit Feedback via Group-Aware User Behavior Simulation](https://mlsanity.com/paper/2508.05709/) (2025)
- [Beyond Isolated Investor: Predicting Startup Success via Roleplay-Based Collective Agents](https://mlsanity.com/paper/2512.22608/) (2025)
- [Evaluation of Agents under Simulated AI Marketplace Dynamics](https://mlsanity.com/paper/2604.14256/) (2026)
- [KnowSim: Evaluating Information Calibration in LLM Assistants with User Simulators that Learn](https://mlsanity.com/paper/2608.17150/) (2026)
- [LatentCRS: A Variational EM Framework for Bridging Semantics and Behavior in LLM-based Conversational Recommendation](https://mlsanity.com/paper/2503.10703/) (2025)
- [Dagstuhl Perspectives Workshop 24352 -- Conversational Agents: A Framework for Evaluation (CAFE): Manifesto](https://mlsanity.com/paper/2506.11112/) (2025)
- [In-Browser Agents for Search Assistance](https://mlsanity.com/paper/2601.09928/) (2026)
- [Same Outcomes, Different Journeys: A Trace-Level Framework for Comparing Human and GUI-Agent Behavior in Production Search Systems](https://mlsanity.com/paper/2604.07929/) (2026)
- [BehaviorBench: Modeling Real-World User Decisions from Behavioral Traces](https://mlsanity.com/paper/2606.02798/) (2026)
- [Prompt Optimization for User Simulation in Conversational Recommender Systems: A Multi-Objective Framework](https://mlsanity.com/paper/2607.00010/) (2026)
- [The "Curse of Knowledge" in LLM Query Simulation: Concept Provenance for Tracing Answer-Side Intrusion](https://mlsanity.com/paper/2608.25245/) (2026)

## Abstract (arXiv)

Due to the advantages in the cost-efficiency and reproducibility, user simulation has become a promising solution to the user-centric evaluation of information retrieval systems. Nonetheless, accurately simulating user search behaviors has long been a challenge, because users' actions in search are highly complex and driven by intricate cognitive processes such as learning, reasoning, and planning. Recently, Large Language Models (LLMs) have demonstrated remarked potential in simulating human-level intelligence and have been used in building autonomous agents for various tasks. However, the potential of using LLMs in simulating search behaviors has not yet been fully explored. In this paper, we introduce a LLM-based user search behavior simulator, USimAgent. The proposed simulator can simulate users' querying, clicking, and stopping behaviors during search, and thus, is capable of generating complete search sessions for specific search tasks. Empirical investigation on a real user behavior dataset shows that the proposed simulator outperforms existing methods in query generation and is comparable to traditional methods in predicting user clicks and stopping behaviors. These results not only validate the effectiveness of using LLMs for user simulation but also shed light on the development of a more robust and generic user simulators. The code and data are accessible at https://github.com/Meow-E/USimAgent.