mlsanityData to 7 Oct 2026

Persona Vectors in Games: Measuring and Steering Strategies via Activation Vectors

arXiv 2603.21398 ↗First posted 22 Mar 2026cs.AI cs.GTcited by 6

Not on the map. Why?

Abstract (arXiv)

Large language models (LLMs) are increasingly deployed as autonomous decision-makers in strategic settings, yet we have limited tools for understanding their high-level behavioral traits. We use activation steering methods in game-theoretic settings, constructing persona vectors for altruism, forgiveness, and expectations of others by contrastive activation addition. Evaluating on canonical games, we find that activation steering systematically shifts both quantitative strategic choices and natural-language justifications. However, we also observe that rhetoric and strategy can diverge under steering. In addition, vectors for self-behavior and expectations of others are partially distinct. Our results suggest that persona vectors offer a promising mechanistic handle on high-level traits in strategic environments.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 8 of its 13 references that are in the map. First posted on arXiv 22 Mar 2026.

Builds on

8 of 13 references.

References · 8

  1. 2023Steering Llama 2 via Contrastive Activation Additioncited by 1,009
  2. 2025Persona Vectors: Monitoring and Controlling Character Traits in Language Modelscited by 303
  3. 2023Playing repeated games with Large Language Modelscited by 213
  4. 2025Which Economic Tasks are Performed with AI? Evidence from Millions of Claude Conversationscited by 88
  5. 2024Nicer Than Humans: How do Large Language Models Behave in the Prisoner's Dilemma?cited by 62
  6. 2024Algorithmic Collusion by Large Language Modelscited by 54
  7. 2023ALYMPICS: LLM Agents Meet Game Theory -- Exploring Strategic Decision-Making with AI Agentscited by 33
  8. 2025Belief Dynamics Reveal the Dual Nature of In-Context Learning and Activation Steeringcited by 24

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 6.

6 papers.

  1. 2026Tracing Persona Vectors Through LLM Pretrainingcited by 3
  2. 2026When Is Rank-1 Steering Cheap? Geometry, Granularity, and Budgeted Searchcited by 1
  3. 2026To Nuke or Not to Nuke: LLMs' (Missing) Ethical Reasoning and Actions in a High-Stakes Decision-Making Simulationcited by 1
  4. 2026How a Cooperative-Override Circuit Suppresses Nash Play in Large Language Modelscited by 0
  5. 2026Symbolic Reasoning Frameworks Trigger Memory-Mediated Ecosystem Dynamics in Multi-Agent LLM Systemscited by 0
  6. 2026Do LLMs Choose Like Humans? Using Cognitive Theory to Evaluate LLM Decision-Makingcited by 0