arXiv Computation and Language
Towards User Simulators That Stay On Task And Still Sound Natural
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv AI
Oct 9
MIMESIS: Learning User Simulators as Training Environments for Interactive Agents
MIMESIS is a user simulator designed to train interactive language agents by mimicking real user behavior. It is trained on human conversations with explicit reasoning supervision and incorporates 13 realistic behavioral patterns. Experiments show that agents trained with MIMESIS outperform those trained with GPT-5.5 across multiple unseen simulators, and the proposed Coached On-Policy Self-Distillation further improves agent performance by providing dense, token-level supervision.
arXiv Computation and Language
Oct 12
Training User Simulators with Latent Intrinsic Feedback
The paper introduces user simulators that provide intrinsic feedback by incorporating latent evaluation states such as internal thoughts, reactions, and scalar ratings. These simulators, trained on real user–assistant interaction logs, outperform prompted baselines in realism and critiquing behaviors, and their turn‑level evaluations better align with human judgments. Additionally, the intrinsic feedback serves as an effective reward signal for multi‑turn reinforcement learning, reducing compute requirements by over 50% compared to setups using external judge LLMs.
arXiv AI
Sep 25
Beyond Surface Style: Aligning Multi-Turn User Simulators with Behavioral Consistency
The paper introduces TRACER, a multi‑turn user simulator that models evolving user intent and aligns simulated behavior with real interaction trajectories. TRACER is trained first with supervised fine‑tuning on real dialogues and then with reinforcement learning that uses hierarchical outcome‑ and trajectory‑level rewards to address reward sparsity and credit assignment. In real customer‑service sessions, TRACER‑7B outperforms the best baseline by 11.4 conversion F1, achieves the lowest group‑level conversion‑rate error and semantic trajectory distance, and generalizes to out‑of‑distribution scenarios, while human Turing tests show its conversations appear natural. The authors also present the Dynamic Marketing Benchmark, which evaluates both persuasion effectiveness and response quality of large language models through simulated interactions, demonstrating that higher response quality does not always lead to higher conversion rates.
arXiv Computation and Language
5d ago
Learning User Representations to Improve Simulation Fidelity
The paper introduces UserRepGen-4B, a representation generator that creates natural-language user representations to condition user simulators for more faithful conversation simulation. By formulating a conversation reconstruction task and using hindsight distillation, the system learns to generate representations that improve simulation fidelity across 700 conversations from seven datasets. The improved representations also enhance diversity preservation and user distinction in unseen tasks.
arXiv Computation and Language
Oct 12
MADS: Multi-Agent Dialog Simulation for Robust Conversational Agents
MADS (Multi-Agent Dialog Simulation) is a synthetic data generation pipeline that creates structured, diverse dialogue trajectories, including adversarial conversations that reflect realistic failure scenarios. The resulting MADS-Bench benchmark covers six domains, 55 personas, and 1095 conversations, with about 66% featuring failure-prone situations. Models trained with MADS are evaluated using a two-stage approach combining supervised fine-tuning and reinforcement learning with verifiable rewards to assess robustness.
arXiv Computation and Language
Oct 5
CUEing User Simulators: Calibrated User Embeddings for Multi-Turn Benchmarking
The paper introduces Calibrated User Embeddings (CUE), a framework that encodes real user sessions into continuous representations and decodes them into persona commands to steer large language models (LLMs) as user simulators without additional training. CUE enables user-conditioned replay of past interactions and generates novel personas that better align with real-user success rates and failure patterns. Evaluations on the τ²‑Bench dataset show that CUE‑driven simulators commit fewer simulator‑attributed errors, more accurately reproduce real‑user failure modes, and maintain competitive user fidelity across various tasks and LLMs.