SPASM: Stable Persona-driven Agent Simulation for Multi-turn Dialogue Generation

• URL: http://arxiv.org/abs/2604.09212v1
• Date: Fri, 10 Apr 2026 11:05:12 GMT
• Title: SPASM: Stable Persona-driven Agent Simulation for Multi-turn Dialogue Generation
• Abstract summary: Large language models are increasingly deployed in multi-turn settings such as tutoring, support, and counseling.<n>LLM conversations can accumulate identity-related failures such as persona drift, role confusion, and "echoing"<n>We introduce SPASM, a modular framework that decomposes simulation into (i) persona creation via schema sampling, plausibility validation, and natural-language persona crafting.
• Score: 4.663948718816864
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models are increasingly deployed in multi-turn settings such as tutoring, support, and counseling, where reliability depends on preserving consistent roles, personas, and goals across long horizons. This requirement becomes critical when LLMs are used to generate synthetic dialogues for training and evaluation, since LLM--LLM conversations can accumulate identity-related failures such as persona drift, role confusion, and "echoing", where one agent gradually mirrors its partner. We introduce SPASM (Stable Persona-driven Agent Simulation for Multi-turn dialogue generation), a modular, stability-first framework that decomposes simulation into (i) persona creation via schema sampling, plausibility validation, and natural-language persona crafting, (ii) Client--Responder dialogue generation, and (iii) termination detection for coherent stopping. To improve long-horizon stability without changing model weights, we propose Egocentric Context Projection (ECP): dialogue history is stored in a perspective-agnostic representation and deterministically projected into each agent's egocentric view before generation. Across three LLM backbones (GPT-4o-mini, DeepSeek-V3.2, Qwen-Plus) and nine Client--Responder pairings, we construct a dataset of 4,500 personas and 45,000 conversations (500 personas X 10 conversations per pairing). Ablations show ECP substantially reduces persona drift and, under human validation, eliminates echoing; embedding analyses recover persona structure and reveal strong responder-driven interaction geometry. Our code is available at https://github.com/lhannnn/SPASM.

Related papers

• Consistently Simulating Human Personas with Multi-Turn Reinforcement Learning [52.07170679746533]
  Large Language Models (LLMs) are increasingly used to simulate human users in interactive settings such as therapy, education, and social role-play.<n>We introduce a unified framework for evaluating and improving persona consistency in LLM-generated dialogue.<n>We define three automatic metrics: prompt-to-line consistency, line-to-line consistency, and Q&A consistency, that capture different types of persona drift and validate each against human annotations.
  arXiv  Detail & Related papers  (2025-10-31T19:40:41Z)
• TwinVoice: A Multi-dimensional Benchmark Towards Digital Twins via LLM Persona Simulation [55.55404595177229]
  Large Language Models (LLMs) are exhibiting emergent human-like abilities.<n>TwinVoice is a benchmark for assessing persona simulation across diverse real-world contexts.
  arXiv  Detail & Related papers  (2025-10-29T14:00:42Z)
• A Framework for Generating Conversational Recommendation Datasets from Behavioral Interactions [2.0693204407592836]
  We present ConvRecStudio, a framework that simulates realistic, multi-turn dialogs grounded in timestamped user-item interactions and reviews.<n>We apply ConvRecStudio to three domains -- MobileRec, Yelp, and Amazon Electronics -- producing over 12K multi-turn dialogs per dataset.
  arXiv  Detail & Related papers  (2025-06-14T22:58:48Z)
• A Personalized Conversational Benchmark: Towards Simulating Personalized Conversations [112.81207927088117]
  PersonaConvBench is a benchmark for evaluating personalized reasoning and generation in multi-turn conversations with large language models (LLMs)<n>We benchmark several commercial and open-source LLMs under a unified prompting setup and observe that incorporating personalized history yields substantial performance improvements.
  arXiv  Detail & Related papers  (2025-05-20T09:13:22Z)
• REALTALK: A 21-Day Real-World Dataset for Long-Term Conversation [51.97224538045096]
  We introduce REALTALK, a 21-day corpus of authentic messaging app dialogues.<n>We compare EI attributes and persona consistency to understand the challenges posed by real-world dialogues.<n>Our findings reveal that models struggle to simulate a user solely from dialogue history, while fine-tuning on specific user chats improves persona emulation.
  arXiv  Detail & Related papers  (2025-02-18T20:29:01Z)
• Exploring the Potential of Large Language Models to Simulate Personality [39.58317527488534]
  We aim to simulate personal traits according to the Big Five model with the use of large language models (LLMs)<n>We present a dataset of generated texts with the predefined Big Five characteristics and provide an analytical framework for testing LLMs on a simulation of personality skills.
  arXiv  Detail & Related papers  (2025-02-12T10:17:18Z)
• X-TURING: Towards an Enhanced and Efficient Turing Test for Long-Term Dialogue Agents [56.64615470513102]
  The Turing test examines whether AIs exhibit human-like behaviour in natural language conversations.<n>Traditional setting limits each participant to one message at a time and requires constant human participation.<n>This paper proposes textbftextscX-Turing, which enhances the original test with a textitburst dialogue pattern.
  arXiv  Detail & Related papers  (2024-08-19T09:57:28Z)
• Hello Again! LLM-powered Personalized Agent for Long-term Dialogue [63.65128176360345]
  We introduce a model-agnostic framework, the Long-term Dialogue Agent (LD-Agent)<n>It incorporates three independently tunable modules dedicated to event perception, persona extraction, and response generation.<n>The effectiveness, generality, and cross-domain capabilities of LD-Agent are empirically demonstrated.
  arXiv  Detail & Related papers  (2024-06-09T21:58:32Z)

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.