# Role Steering of Language Models for Social Simulations

arXiv: https://arxiv.org/abs/2608.00023 · HTML: https://mlsanity.com/paper/2608.00023/

## Key facts

- Cited by 1 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 25 of its 30 references that are in the map.
- First posted on arXiv 9 Jul 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, 25 of 25)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [The Linear Representation Hypothesis and the Geometry of Large Language Models](https://mlsanity.com/paper/2311.03658/) (2023)
- [Prometheus: Inducing Fine-grained Evaluation Capability in Language Models](https://mlsanity.com/paper/2310.08491/) (2023)
- [Persona Vectors: Monitoring and Controlling Character Traits in Language Models](https://mlsanity.com/paper/2507.21509/) (2025)
- [Role-Play with Large Language Models](https://mlsanity.com/paper/2305.16367/) (2023)
- [Analyzing the Generalization and Reliability of Steering Vectors](https://mlsanity.com/paper/2407.12404/) (2024)
- [The Assistant Axis: Situating and Stabilizing the Default Persona of Language Models](https://mlsanity.com/paper/2601.10387/) (2026)
- [Measuring and Controlling Instruction (In)Stability in Language Model Dialogs](https://mlsanity.com/paper/2402.10962/) (2024)
- [A Unified Understanding and Evaluation of Steering Methods](https://mlsanity.com/paper/2502.02716/) (2025)
- [The Prompt Makes the Person(a): A Systematic Evaluation of Sociodemographic Persona Prompting for Large Language Models](https://mlsanity.com/paper/2507.16076/) (2025)
- [Persistent Instability in LLM's Personality Measurements: Effects of Scale, Reasoning, and Conversation History](https://mlsanity.com/paper/2508.04826/) (2025)
- [Online Adaptive Policy Selection in Time-Varying Systems: No-Regret via Contractive Perturbations](https://mlsanity.com/paper/2210.12320/) (2022)
- [Mean-Field Sampling for Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2412.00661/) (2024)
- [PersonaEval: Are LLM Evaluators Human Enough to Judge Role-Play?](https://mlsanity.com/paper/2508.10014/) (2025)
- [Online Policy Optimization in Unknown Nonlinear Systems](https://mlsanity.com/paper/2404.13009/) (2024)
- [Peer-to-Peer Learning Dynamics of Wide Neural Networks](https://mlsanity.com/paper/2409.15267/) (2024)
- [What Can We Actually Steer? A Multi-Behavior Study of Activation Control](https://mlsanity.com/paper/2511.18284/) (2025)
- [Continuous Latent Contexts Enable Efficient Online Learning in Transformers](https://mlsanity.com/paper/2605.09867/) (2026)
- [Training Generalizable Collaborative Agents via Strategic Risk Aversion](https://mlsanity.com/paper/2602.21515/) (2026)
- [Learning Approximate Nash Equilibria in Cooperative Multi-Agent Reinforcement Learning via Mean-Field Subsampling](https://mlsanity.com/paper/2603.03759/) (2026)
- [Structure from Strategic Interaction & Uncertainty: Risk Sensitive Games for Robust Preference Learning](https://mlsanity.com/paper/2605.09946/) (2026)

## Built on by (most cited first, 1 of 1)

- [Back in Style: A Sociolinguistic Approach to Authoring and Measuring Persona Fidelity in User Simulation](https://mlsanity.com/paper/2610.10988/) (2026)

## Abstract (arXiv)

Social simulations built from language-model agents need role-conditioned behavior that can be checked before agents are placed into a simulated population. We introduce an activation-steering screening workflow for role-conditioned agents: define a role profile, extract a role-specific direction, sweep four steering coefficients, evaluate role-profile alignment, and pass or flag each candidate configuration. On OLMo-3-7B-Instruct, we apply the workflow to a mixed 275-role inventory with 228 role-agnostic questions, GPT-4.1-mini prompted role references, and GPT-4.1-mini judges. Role-specific directions receive higher judged role-profile alignment than an assistant-axis directional control from prior persona-vector work, with mean overall scores of 63.2 versus 41.1 across the tested grid. They also preserve high lexical diversity, while the control drops sharply at larger coefficients. The role-level screen is the main practical output: most roles improve as steering increases, but 38 roles decline across all six measured dimensions, showing why simulation builders should choose coefficients per role rather than deploy a uniform high-strength setting. We make our code and evaluation artifacts available at https://anonymous.4open.science/r/anonymous-research-code-5F03/.