mlsanityData to 7 Oct 2026

HARBOR: Exploring Persona Dynamics in Multi-Agent Competition

arXiv 2502.12149 ↗First posted 17 Feb 2025cs.MA cs.AI cs.CLcited by 6

On the map: LLM agents and tool use → Financial trading and forecasting agents

Abstract (arXiv)

We investigate factors contributing to LLM agents' success in competitive multi-agent environments, using auctions as a testbed where agents bid to maximize profit. The agents are equipped with bidding domain knowledge, distinct personas that reflect item preferences, and a memory of auction history. Our work extends the classic auction scenario by creating a realistic environment where multiple agents bid on houses, weighing aspects such as size, location, and budget to secure the most desirable homes at the lowest prices. Particularly, we investigate three key questions: (a) How does a persona influence an agent's behavior in a competitive setting? (b) Can an agent effectively profile its competitors' behavior during auctions? (c) How can persona profiling be leveraged to create an advantage using strategies such as theory of mind? Through a series of experiments, we analyze the behaviors of LLM agents and shed light on new findings. Our testbed, called HARBOR, offers a valuable platform for deepening our understanding of multi-agent workflows in competitive environments.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Placed in Financial trading and forecasting agents, one of 16 directions in LLM agents and tool use. Builds on 55 of its 132 references that are in the map. First posted on arXiv 17 Feb 2025.

Builds on

55 of 132 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Put Your Money Where Your Mouth Is: Evaluating Strategic Planning and Execution of LLM Agents in an Auction Arena9 Oct

Other references · 54

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  2. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  3. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  4. 2023WebArena: A Realistic Web Environment for Building Autonomous Agentscited by 1,908
  5. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,906
  6. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  7. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,348
  8. 2024OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environmentscited by 1,134
  9. 2025Multi-Agent Collaboration Mechanisms: A Survey of LLMscited by 424
  10. 2024Justice or Prejudice? Quantifying Biases in LLM-as-a-Judgecited by 354
  11. 2023On the Planning Abilities of Large Language Models : A Critical Investigationcited by 308
  12. 2024TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Taskscited by 306
38 more
  1. 2023Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaborationcited by 246
  2. 2023Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology Viewcited by 221
  3. 2022Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMscited by 220
  4. 2024From Persona to Personalization: A Survey on Role-Playing Language Agentscited by 206
  5. 2024Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalizationcited by 203
  6. 2024Chain of Agents: Large Language Models Collaborating on Long-Context Taskscited by 201
  7. 2023Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMscited by 191
  8. 2024Agent S: An Open Agentic Framework that Uses Computers Like a Humancited by 182
  9. 2024Quantifying the Persona Effect in LLM Simulationscited by 164
  10. 2018Decoupling Strategy and Generation in Negotiation Dialoguescited by 156
  11. 2024Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Makingcited by 142
  12. 2024Hello Again! LLM-powered Personalized Agent for Long-term Dialoguecited by 121
  13. 2024Can LLM be a Personalized Judge?cited by 99
  14. 2023Can Large Language Models Serve as Rational Players in Game Theory? A Systematic Analysiscited by 91
  15. 2024SOTOPIA-π: Interactive Learning of Socially Intelligent Language Agentscited by 89
  16. 2024PersonaGym: Evaluating Persona Agents and LLMscited by 89
  17. 2025PlanGenLLMs: A Modern Survey of LLM Planning Capabilitiescited by 82
  18. 2023How FaR Are Large Language Models From Agents with Theory-of-Mind?cited by 75
  19. 2023CompeteAI: Understanding the Competition Dynamics in Large Language Model-based Agentscited by 65
  20. 2024Determinants of LLM-assisted Decision-Makingcited by 55
  21. 2024Game-theoretic LLM: Agent Workflow for Negotiation Gamescited by 55
  22. 2024NegotiationToM: A Benchmark for Stress-testing Machine Theory of Mind on Negotiation Surroundingcited by 49
  23. 2024Large Language Models Assume People are More Rational than We Really arecited by 49
  24. 2023Theory of Mind in Large Language Models: Examining Performance of 11 State-of-the-Art models vs. Children Aged 7-10 on Advanced Testscited by 46
  25. 2024Evaluating Language Model Agency through Negotiationscited by 43
  26. 2024Beyond Demographics: Aligning Role-playing LLM-based Agents Using Human Belief Networkscited by 39
  27. 2020Improving Dialog Systems for Negotiation with Personality Modelingcited by 37
  28. 2023Deciphering Digital Detectives: Understanding LLM Behaviors and Capabilities in Multi-Agent Mystery Gamescited by 29
  29. 2024Persona is a Double-edged Sword: Mitigating the Negative Impact of Role-playing Prompts in Zero-shot Reasoning Taskscited by 28
  30. 2024LLMs are Biased Teachers: Evaluating LLM Bias in Personalized Educationcited by 28
  31. 2024Building Better AI Agents: A Provocation on the Utilisation of Persona in LLM-based Conversational Agentscited by 26
  32. 2024Do LLMs Exhibit Human-Like Reasoning? Evaluating Theory of Mind in LLMs for Open-Ended Responsescited by 22
  33. 2024SelfGoal: Your Language Agents Already Know How to Achieve High-level Goalscited by 21
  34. 2024POGEMA: A Benchmark Platform for Cooperative Multi-Agent Pathfindingcited by 20
  35. 2024Evaluating and Enhancing LLMs Agent based on Theory of Mind in Guandan: A Multi-Player Cooperative Game under Imperfect Informationcited by 20
  36. 2021RESPER: Computationally Modelling Resisting Strategies in Persuasive Conversationscited by 18
  37. 2024Mutual Theory of Mind in Human-AI Collaboration: An Empirical Study with LLM-driven AI Agents in a Real-time Shared Workspace Taskcited by 17
  38. 2024Planning in Strawberry Fields: Evaluating and Improving the Planning and Scheduling Capabilities of LRM o1cited by 17

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 4; 2026: 2.

6 papers.

  1. 2026AgenticPay: A Multi-Agent LLM Negotiation System for Buyer-Seller Transactionscited by 11
  2. 2025Moloch's Bargain: Emergent Misalignment When LLMs Compete for Audiencescited by 7
  3. 2025Do Persona-Infused LLMs Affect Performance in a Strategic Reasoning Game?cited by 3
  4. 2025PersonaAgent with GraphRAG: Community-Aware Knowledge Graphs for Personalized LLMcited by 2
  5. 2025Shall We Play a Game? Language Models for Open-ended Wargamescited by 1
  6. 2026Aligned Agents, Biased Swarm: Measuring Bias Amplification in Multi-Agent Systemscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026Can LLM Agents Price Competitively? A Dynamic Multi-Attribute Auction Benchmark for Agentic Commerce
  2. 2025Magentic Marketplace: An Open-Source Environment for Studying Agentic Markets
  3. 2025LLM Bidders Preserve the Mechanism-Level Orderings of Human Bidders
  4. 2026Competitive Market Behavior of LLMs
  5. 2025Evaluating LLM Agent Collusion in Double Auctions
  6. 2026Strategic Exploitation in LLM Agent Markets: A Simulation Framework for E-Commerce Trust
  7. 2026Engineering Simplicity: Simple Mechanism Interfaces Steer LLM Agents
  8. 2025neuralFOMO: Can LLMs Handle Being Second Best? Measuring Envy-Like Preferences in Multi-Agent Settings