Measuring and Mitigating the Distributional Gap Between Real and Simulated User Behaviors

• URL: http://arxiv.org/abs/2605.07847v1
• Date: Fri, 08 May 2026 15:09:25 GMT
• Title: Measuring and Mitigating the Distributional Gap Between Real and Simulated User Behaviors
• Abstract summary: We introduce a method to measure the distributional gap between real and simulated user behaviors.<n>Given a dataset of real and simulated conversations, our method extracts representations of user behavior from each conversation.<n>We show that most simulators behave similarly, while a few stand apart.
• Score: 61.610957638373826
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As user simulators are increasingly used for interactive training and evaluation of AI assistants, it is essential that they represent the diverse behaviors of real users. While existing works train user simulators to generate human-like responses, whether they capture the broad and heterogeneous distribution of real user behaviors remains an open question. In this work, we introduce a method to measure the distributional gap between real and simulated user behaviors, validated through a human study and ablations. Given a dataset of real and simulated conversations, our method extracts representations of user behavior from each conversation, quantizes them into discrete distributions via clustering, then computes divergence metrics. We provide the first systematic evaluation of 24 LLM-based user simulators on coding and writing tasks, and reveal a large distributional gap from real users that varies across model families, scales, and behavioral facets. Pairwise comparisons show that most simulators behave similarly, while a few stand apart. Combining behaviorally complementary simulators brings the resulting distribution closer to real users compared to either simulator on its own. Finally, a TF-IDF analysis of the clusters surfaces interpretable patterns of behaviors that simulators capture, miss, and hallucinate.

Related papers

• LiveSim: Simulating Environment-Shaped Users in Multi-Agent Live-Stream Ecosystems [53.47971344451318]
  We propose textbfLiveSim, an LLM-based framework for live-stream ecosystem simulation.<n>It represents users as editable behavioral hypotheses and progressively refines them through trajectory-grounded interactions.<n>Experiments on real-world live-stream risk-control data validate the effectiveness of LiveSim in improving user-level behavioral fidelity.
  arXiv  Detail & Related papers  (2026-08-27T09:16:29Z)
• Beyond Action Imitation: Learning a Decision-Aware User Simulator for Online Advertising [47.726568328425394]
  DASH is a decision-aware user simulator that jointly generates thinking traces and predicts behavioral actions from heterogeneous cross-domain histories.<n>To train a user simulator, DASH distills thinking trajectories from strong LLMs as SFT data.<n>To train a user simulator, DASH tailors a rubric-based reward model that evaluates thinking traces along form, content, and logic for RL training.
  arXiv  Detail & Related papers  (2026-07-29T13:25:30Z)
• Beyond Cooperative Simulators: Generating Realistic User Personas for Robust Evaluation of LLM Agents [28.85410475505536]
  Persona Policies (PPol) is a control layer that induces realistic behavioral variation in user simulators.<n>PPol produces a diverse population of human-like personas for any task in the domain.<n>Agents trained with PPol are more robust to challenging, out-of-distribution behaviors, improving task success by +17% relative to training only on existing simulated interactions.
  arXiv  Detail & Related papers  (2026-05-13T02:16:51Z)
• Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces [81.41397370235102]
  We introduce OmniBehavior, the first user simulation benchmark constructed entirely from real-world data.<n>We show that current models struggle to accurately simulate complex behaviors, with performance plateauing even as context windows expand.<n>This results in the loss of individual differences and long-tail behaviors, highlighting critical directions for future high-fidelity simulation research.
  arXiv  Detail & Related papers  (2026-04-09T15:26:21Z)
• Mind the Sim2Real Gap in User Simulation for Agentic Tasks [101.69142591891234]
  We formalize the Sim2Real gap in user simulation and present the first study running the full $$-bench protocol with real humans.<n> Behaviorally, LLM simulators are excessively cooperative, stylistically uniform, and lack realistic frustration or ambiguity.<n>These findings highlight the importance of human validation when using LLM-based user simulators in the agent development cycle.
  arXiv  Detail & Related papers  (2026-03-11T19:12:31Z)
• ConvApparel: A Benchmark Dataset and Validation Framework for User Simulators in Conversational Recommenders [48.83868690303791]
  We introduce ConvApparel, a new dataset of human-AI conversations designed to address this gap.<n>Its unique dual-agent data collection protocol -- using both "good" and "bad" recommenders -- enables counterfactual validation.<n>We propose a comprehensive validation framework that combines statistical alignment, a human-likeness score, and counterfactual validation.
  arXiv  Detail & Related papers  (2026-02-18T23:00:21Z)
• HumanLM: Simulating Users with State Alignment Beats Response Imitation [84.89761487596844]
  We propose a novel training framework, HumanLM, which builds user simulators that accurately reflect real users.<n>HumanLM generates natural-language latent states that align with ground-truth responses through reinforcement learning.<n>For extensive evaluation, we develop Humanual, a comprehensive benchmark for simulating real users based on public data.
  arXiv  Detail & Related papers  (2026-02-07T20:26:28Z)
• PUB: An LLM-Enhanced Personality-Driven User Behaviour Simulator for Recommender System Evaluation [9.841963696576546]
  Personality-driven User Behaviour Simulator (PUB) integrates the Big Five personality traits to model personalised user behaviour.<n>PUB dynamically infers user personality from behavioural logs (e.g., ratings, reviews) and item metadata, then generates synthetic interactions that preserve statistical fidelity to real-world data.<n> Experiments on the Amazon review datasets show that logs generated by PUB closely align with real user behaviour and reveal meaningful associations between personality traits and recommendation outcomes.
  arXiv  Detail & Related papers  (2025-06-05T01:57:36Z)
• Know You First and Be You Better: Modeling Human-Like User Simulators via Implicit Profiles [37.43150003866563]
  We introduce the User Simulator with Implicit Profiles (USP), a framework that infers implicit user profiles from human-machine interactions to simulate personalized and realistic dialogues.<n>USP outperforms strong baselines in terms of authenticity and diversity while maintaining comparable consistency.
  arXiv  Detail & Related papers  (2025-02-26T09:26:54Z)
• User Behavior Simulation with Large Language Model based Agents [116.74368915420065]
  We propose an LLM-based agent framework and design a sandbox environment to simulate real user behaviors. Based on extensive experiments, we find that the simulated behaviors of our method are very close to the ones of real humans.
  arXiv  Detail & Related papers  (2023-06-05T02:58:35Z)

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.