PersonaForge: Realistic Multi-Turn User Simulation for Agentic Systems

• URL: http://arxiv.org/abs/2608.28378v1
• Date: Fri, 28 Aug 2026 14:33:19 GMT
• Title: PersonaForge: Realistic Multi-Turn User Simulation for Agentic Systems
• Abstract summary: We introduce textbfPersonaForge, a user simulation framework for synthesizing realistic multi-turn user--agent interactions.<n>Using PersonaForge, we construct a 6.3K-record training dataset and textbfPersonaForge-Bench, a manually annotated 138-task benchmark.<n>Experiments show that PersonaForge training improves the composite score by +4.1%, with gains across all four dimensions.
• Score: 53.65117408512214
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models are increasingly used as agentic workflow executors, yet existing training data and benchmarks largely assume informationally complete, single-turn queries. Our analysis of 16K real-world sessions shows that 75.9% of interactions are multi-turn, revealing a substantial gap between how users interact with agents and how such systems are trained and evaluated. We introduce \textbf{PersonaForge}, a user simulation framework for synthesizing realistic multi-turn user--agent interactions. PersonaForge combines a four-dimensional persona space, SOUL-driven behavioral control calibrated to real-user statistics, and Reverse Deep Construction grounded in authentic seed queries. Using PersonaForge, we construct a 6.3K-record training dataset and \textbf{PersonaForge-Bench}, a manually annotated 138-task benchmark spanning over 20 professional domains with four-dimensional scoring. Experiments on Qwen3.5-27B show that PersonaForge training improves the composite score by +4.1%, with gains across all four dimensions and the largest improvements in Task Completion (+6.0%) and Response Quality (+6.8%). Further analyses show that PersonaForge-trained agents use fewer turns and tool calls, suggesting improved interaction efficiency, while ablations confirm the contribution of SOUL components and adaptive simulation. Together, PersonaForge and PersonaForge-Bench establish a foundation for training and evaluating agents under realistic multi-turn user interaction.

Related papers

• A Three-Tier Persona Vector for Controllable User Simulation in Agentic Evaluation [0.9918136378822991]
  We propose a three-tier persona vector with 23 operationalized dimensions.<n>We evaluate the persona model inside a synthetic data generation pipeline across 64,698 conversations.
  arXiv  Detail & Related papers  (2026-09-08T11:28:02Z)
• Efficient Test-Time Adaptation through Human-AI Interaction [112.5131603022122]
  We propose test-time adaptation through human-agent interaction (TAHI)<n>We adapt agents to 30 individuals in two high-utility domains, writing and visual creation, on a total of 600 tasks.<n>Our agents improve solo task success by 4.5-20.9% within only tens of tasks.
  arXiv  Detail & Related papers  (2026-09-03T17:33:18Z)
• OdysSim: Building Foundation Models for Human Behavior Simulation [70.35265860287608]
  Large language models are increasingly deployed as human simulators for interactive evaluation and social simulation.<n>Yet helpfulness-driven post-training pulls them toward a homogeneous, overly agreeable assistant register.<n>We present OdysSim, the largest open systematic investigation of behavioral foundation models.
  arXiv  Detail & Related papers  (2026-06-12T07:31:55Z)
• EgoBench: An Interactive Egocentric Multimodal Benchmark for Tool-Using Agents [17.727481701114556]
  We introduce EgoBench, the first interactive multimodal benchmark for tool-using agents.<n>We implement a three-stage synergistic pipeline through which each task is designed to enforce the joint application of visual perception and tool-augmented multi-hop reasoning.<n>We additionally develop a multi-agent simulated user within EgoBench to evaluate agents' interaction capabilities, which generates high-fidelity, task-aligned responses.
  arXiv  Detail & Related papers  (2026-05-27T01:28:15Z)
• One Battle After Another: Probing LLMs' Limits on Multi-Turn Instruction Following with a Benchmark Evolving Framework [51.50565654314582]
  Large language models can follow users' instructions throughout a dialogue spanning multiple topics.<n>Existing benchmarks are often limited to a fixed number of turns, making them susceptible to saturation and failing to account for the user's interactive experience.<n>We propose a framework for assessing multi-turn instruction-following ability.
  arXiv  Detail & Related papers  (2025-11-05T14:39:59Z)
• One Model to Critique Them All: Rewarding Agentic Tool-Use via Efficient Reasoning [54.580646706013965]
  Reward models (RMs) play a critical role in aligning large language models with human preferences.<n>We introduce ToolRM, a family of lightweight generative RMs tailored for general tool-use scenarios.<n>To build these models, we propose a novel pipeline that constructs pairwise preference data using rule-based scoring and multidimensional sampling.
  arXiv  Detail & Related papers  (2025-10-30T06:08:27Z)
• PersonaX: A Recommendation Agent Oriented User Modeling Framework for Long Behavior Sequence [8.557534799079956]
  PersonaX is an agent-agnostic LLM-UM framework to address these challenges.<n>It augments downstream recommendation agents to achieve better recommendation performance and inference efficiency.
  arXiv  Detail & Related papers  (2025-03-04T08:41:40Z)
• 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)
• Simulating User Agents for Embodied Conversational-AI [9.402740034754455]
  We build a large language model (LLM)-based user agent that can simulate user behavior during interactions with an embodied agent. We evaluate our user agent's ability to generate human-like behaviors by comparing its simulated dialogues with the TEACh dataset.
  arXiv  Detail & Related papers  (2024-10-31T00:56:08Z)
• Tool-Augmented Reward Modeling [58.381678612409]
  We propose a tool-augmented preference modeling approach, named Themis, to address limitations by empowering RMs with access to external environments. Our study delves into the integration of external tools into RMs, enabling them to interact with diverse external sources. In human evaluations, RLHF trained with Themis attains an average win rate of 32% when compared to baselines.
  arXiv  Detail & Related papers  (2023-10-02T09:47:40Z)
• MUG: Interactive Multimodal Grounding on User Interfaces [12.035123646959669]
  We present MUG, a novel interactive task for multimodal grounding where a user and an agent work collaboratively on an interface screen. Prior works modeled multimodal UI grounding in one round: the user gives a command and the agent responds to the command. MUG allows multiple rounds of interactions such that upon seeing the agent responses, the user can give further commands for the agent to refine or even correct its actions.
  arXiv  Detail & Related papers  (2022-09-29T21:08:18Z)

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.