Choose Your Agent: Tradeoffs in Adopting AI Advisors, Coaches, and Delegates in Multi-Party Negotiation

• URL: http://arxiv.org/abs/2602.12089v2
• Date: Fri, 13 Feb 2026 18:08:38 GMT
• Title: Choose Your Agent: Tradeoffs in Adopting AI Advisors, Coaches, and Delegates in Multi-Party Negotiation
• Authors: Kehang Zhu, Nithum Thain, Vivian Tsai, James Wexler, Crystal Qian,
• Abstract summary: We present an online behavioral experiment in which participants play three multi-turn bargaining games in groups of three.<n>Each game grants access to a single LLM assistance modality: proactive recommendations from an Advisor, reactive feedback from a Coach, or autonomous execution by a Delegate.<n>Despite preferring the Advisor modality, participants achieve the highest mean individual gains with the Delegate, demonstrating a preference-performance misalignment.<n>Our research reveals a gap between agent capabilities and realized group welfare.
• Score: 7.18318917618808
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As AI usage becomes more prevalent in social contexts, understanding agent-user interaction is critical to designing systems that improve both individual and group outcomes. We present an online behavioral experiment (N = 243) in which participants play three multi-turn bargaining games in groups of three. Each game, presented in randomized order, grants access to a single LLM assistance modality: proactive recommendations from an Advisor, reactive feedback from a Coach, or autonomous execution by a Delegate; all modalities are powered by an underlying LLM that achieves superhuman performance in an all-agent environment. On each turn, participants privately decide whether to act manually or use the AI modality available in that game. Despite preferring the Advisor modality, participants achieve the highest mean individual gains with the Delegate, demonstrating a preference-performance misalignment. Moreover, delegation generates positive externalities; even non-adopting users in access-to-delegate treatment groups benefit by receiving higher-quality offers. Mechanism analysis reveals that the Delegate agent acts as a market maker, injecting rational, Pareto-improving proposals that restructure the trading environment. Our research reveals a gap between agent capabilities and realized group welfare. While autonomous agents can exhibit super-human strategic performance, their impact on realized welfare gains can be constrained by interfaces, user perceptions, and adoption barriers. Assistance modalities should be designed as mechanisms with endogenous participation; adoption-compatible interaction rules are a prerequisite to improving human welfare with automated assistance.

Related papers

• Pushing Forward Pareto Frontiers of Proactive Agents with Behavioral Agentic Optimization [61.641777037967366]
  Proactive large language model (LLM) agents aim to actively plan, query, and interact over multiple turns.<n>Agentic reinforcement learning (RL) has emerged as a promising solution for training such agents in multi-turn settings.<n>We propose BAO, an agentic RL framework that combines behavior enhancement to enrich proactive reasoning and information-gathering capabilities.
  arXiv  Detail & Related papers  (2026-02-11T20:40:43Z)
• Ad Insertion in LLM-Generated Responses [16.434649348378706]
  We propose a practical framework that resolves tensions through two decoupling strategies.<n>First, we decouple ad insertion from response generation to ensure safety and explicit disclosure.<n>Second, we decouple bidding from specific user queries by using genres'' (high-level semantic clusters) as a proxy.
  arXiv  Detail & Related papers  (2026-01-27T10:16:03Z)
• From Individual to Multi-Agent Algorithmic Recourse: Minimizing the Welfare Gap via Capacitated Bipartite Matching [9.37591403853433]
  We introduce a novel framework for multi-agent algorithmic recourse that accounts for multiple recourse seekers and recourse providers.<n>Our framework enables the many-to-many algorithmic recourse to achieve near-optimal welfare with minimum modification in system settings.
  arXiv  Detail & Related papers  (2025-08-14T21:04:24Z)
• Exploring Big Five Personality and AI Capability Effects in LLM-Simulated Negotiation Dialogues [16.07828032939124]
  This paper presents an evaluation framework for agentic AI systems in mission-critical negotiation contexts.<n>Using Sotopia as a simulation testbed, we present two experiments that systematically evaluated how personality traits and AI agent characteristics influence social negotiation outcomes.
  arXiv  Detail & Related papers  (2025-06-19T00:14:56Z)
• ASTRA: A Negotiation Agent with Adaptive and Strategic Reasoning via Tool-integrated Action for Dynamic Offer Optimization [5.092928597354372]
  ASTRA is a novel framework for turn-level offer optimization grounded in two core principles: opponent modeling and Tit-for-Tat reciprocity.<n>ASTRA operates in three stages: (1) interpreting counterpart behavior, (2) optimizing counteroffers via a tool-integrated action with a linear programming (LP) solver, and (3) selecting offers based on strategy assessment and the partner's acceptance probability.
  arXiv  Detail & Related papers  (2025-03-10T09:57:50Z)
• Human Decision-making is Susceptible to AI-driven Manipulation [87.24007555151452]
  AI systems may exploit users' cognitive biases and emotional vulnerabilities to steer them toward harmful outcomes.<n>This study examined human susceptibility to such manipulation in financial and emotional decision-making contexts.
  arXiv  Detail & Related papers  (2025-02-11T15:56:22Z)
• Fairness in Agentic AI: A Unified Framework for Ethical and Equitable Multi-Agent System [0.0]
  This paper introduces a novel framework where fairness is treated as a dynamic, emergent property of agent interactions.<n>The framework integrates fairness constraints, bias mitigation strategies, and incentive mechanisms to align autonomous agent behaviors with societal values.
  arXiv  Detail & Related papers  (2025-02-11T04:42:00Z)
• Mixed-Initiative Human-Robot Teaming under Suboptimality with Online Bayesian Adaptation [0.6591036379613505]
  We develop computational modeling and optimization techniques for enhancing the performance of suboptimal human-agent teams. We adopt an online Bayesian approach that enables a robot to infer people's willingness to comply with its assistance in a sequential decision-making game. Our user studies show that user preferences and team performance indeed vary with robot intervention styles.
  arXiv  Detail & Related papers  (2024-03-24T14:38:18Z)
• Beyond Recommender: An Exploratory Study of the Effects of Different AI Roles in AI-Assisted Decision Making [48.179458030691286]
  We examine three AI roles: Recommender, Analyzer, and Devil's Advocate. Our results show each role's distinct strengths and limitations in task performance, reliance appropriateness, and user experience. These insights offer valuable implications for designing AI assistants with adaptive functional roles according to different situations.
  arXiv  Detail & Related papers  (2024-03-04T07:32:28Z)
• Online Decision Mediation [72.80902932543474]
  Consider learning a decision support assistant to serve as an intermediary between (oracle) expert behavior and (imperfect) human behavior. In clinical diagnosis, fully-autonomous machine behavior is often beyond ethical affordances.
  arXiv  Detail & Related papers  (2023-10-28T05:59:43Z)
• AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors [93.38830440346783]
  We propose a multi-agent framework framework that can collaboratively adjust its composition as a greater-than-the-sum-of-its-parts system. Our experiments demonstrate that framework framework can effectively deploy multi-agent groups that outperform a single agent. In view of these behaviors, we discuss some possible strategies to leverage positive ones and mitigate negative ones for improving the collaborative potential of multi-agent groups.
  arXiv  Detail & Related papers  (2023-08-21T16:47:11Z)
• Incentivising cooperation by rewarding the weakest member [0.0]
  greedy strategies can reduce the positive outcome for all agents. In complex situations it is far easier to design machine learning objectives for selfish strategies than for equitable behaviors. We show how this yields fairer'' more equitable behavior, while also maximizing individual outcomes.
  arXiv  Detail & Related papers  (2022-10-04T14:03:37Z)
• A Cooperative-Competitive Multi-Agent Framework for Auto-bidding in Online Advertising [53.636153252400945]
  We propose a general Multi-Agent reinforcement learning framework for Auto-Bidding, namely MAAB, to learn the auto-bidding strategies. Our approach outperforms several baseline methods in terms of social welfare and guarantees the ad platform's revenue.
  arXiv  Detail & Related papers  (2021-06-11T08:07:14Z)
• End-to-End Learning and Intervention in Games [60.41921763076017]
  We provide a unified framework for learning and intervention in games. We propose two approaches, respectively based on explicit and implicit differentiation. The analytical results are validated using several real-world problems.
  arXiv  Detail & Related papers  (2020-10-26T18:39:32Z)
• A Unified Conversational Assistant Framework for Business Process Automation [9.818380332602622]
  Business process automation is a booming multi-billion-dollar industry that promises to remove menial tasks from workers' plates. A simple and user-friendly interface with a low learning curve is necessary to increase the adoption of such agents in banking, insurance, retail and other domains. We present a multi-agent orchestration framework to develop such proactive chatbots by discussing the types of skills that can be composed into agents and how to orchestrate these agents.
  arXiv  Detail & Related papers  (2020-01-07T22:30:05Z)

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.