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

arXiv: https://arxiv.org/abs/2604.09212 · HTML: https://mlsanity.com/paper/2604.09212/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use.
- Builds on 19 of its 53 references that are in the map.
- First posted on arXiv 10 Apr 2026.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 19 of 19)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [An Explanation of In-context Learning as Implicit Bayesian Inference](https://mlsanity.com/paper/2111.02080/) (2021)
- [Enhancing Chat Language Models by Scaling High-quality Instructional Conversations](https://mlsanity.com/paper/2305.14233/) (2023)
- [Persona Vectors: Monitoring and Controlling Character Traits in Language Models](https://mlsanity.com/paper/2507.21509/) (2025)
- [A Survey of Large Language Models for Healthcare: from Data, Technology, and Applications to Accountability and Ethics](https://mlsanity.com/paper/2310.05694/) (2023)
- [Ethical Challenges in Data-Driven Dialogue Systems](https://mlsanity.com/paper/1711.09050/) (2017)
- [Measuring and Controlling Instruction (In)Stability in Language Model Dialogs](https://mlsanity.com/paper/2402.10962/) (2024)
- [On the Loss of Context-awareness in General Instruction Fine-tuning](https://mlsanity.com/paper/2411.02688/) (2024)
- [Echoing: Identity Failures when LLM Agents Talk to Each Other](https://mlsanity.com/paper/2511.09710/) (2025)
- [A Robot-Led Intervention for Emotion Regulation: From Expression to Reappraisal](https://mlsanity.com/paper/2503.18243/) (2025)
- [DialogGuard: Multi-Agent Psychosocial Safety Evaluation of Sensitive LLM Responses](https://mlsanity.com/paper/2512.02282/) (2025)

## Built on by (most cited first, 11 of 11)

- [PHASE-Tree: Modeling Character-State Evolution in Long-Horizon Role-Playing Dialogue](https://mlsanity.com/paper/2608.06975/) (2026)
- [MicroVerse: An Instrument for Measuring Self-Authored Identity Drift in Long-Horizon Multi-Agent Language-Model Simulations](https://mlsanity.com/paper/2608.15844/) (2026)
- [Mind2Dialogue: Training Human-Aware Language Models by Simulating User Mental States](https://mlsanity.com/paper/2609.15972/) (2026)
- [Entropy in Conversational AI: Structured Unpredictability as Inferrable Interiority](https://mlsanity.com/paper/2609.19044/) (2026)
- [Measuring and Improving Behavioral Consistency in Large Language Models through Fact-Heuristic-Emotion State Enforcement](https://mlsanity.com/paper/2607.24765/) (2026)
- [UserToolBench: A User-Profile-Hidden Benchmark for Personalized Decision Making in Tool-Use LLMs](https://mlsanity.com/paper/2608.10042/) (2026)
- [ConVAWG: A Retrieval-Grounded Framework for Controlled Synthetic Dialogue Generation in Violence Against Women and Girls](https://mlsanity.com/paper/2608.11200/) (2026)
- [FiMI Banking: A Sovereign Model for Indian Retail Banking](https://mlsanity.com/paper/2609.03960/) (2026)
- [AnthroDial: Benchmarking LLM Anthropomorphism in Autonomous Social Interaction](https://mlsanity.com/paper/2609.37853/) (2026)
- [Benchmarking Psychological Dynamics in Generative Agents](https://mlsanity.com/paper/2610.04246/) (2026)
- [Uncovering Robustness Weaknesses in LLM Agents via Persona Evolution with Task-Integrity Constraints](https://mlsanity.com/paper/2610.16155/) (2026)

## Abstract (arXiv)

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.