Recent advances in large language models (LLMs) have stimulated growing interest in agent-based recommender systems, enabling language-driven interaction and reasoning for more expressive preference modeling. However, most existing agentic approaches remain predominantly user-centric, treating items as passive entities and neglecting the interests of other critical stakeholders. This limitation exacerbates exposure concentration and long-tail under-representation, threatening long-term system sustainability. In this work, we identify this fundamental limitation and propose the first Tri-party LLM-agent Recommendation framework (TriRec) that explicitly coordinates user utility, item exposure, and platform-level fairness. The framework employs a two-stage architecture: Stage 1 empowers item agents with personalized self-promotion to improve matching quality and alleviate cold-start barriers, while Stage 2 performs platform-level sequential multi-objective re-ranking, balancing user relevance, item utility, and exposure fairness. Experiments show consistent gains in accuracy, fairness, and item-level utility. Moreover, we find that item self-promotion can simultaneously enhance fairness and effectiveness, challenging the conventional trade-off assumption between relevance and fairness. Our code is available at https://github.com/Marfekey/TriRec.

翻译：大语言模型（LLM）的最新进展激发了对基于代理的推荐系统的日益关注，通过语言驱动的交互和推理，实现了更具有表现力的偏好建模。然而，现有的大多数代理方法仍主要围绕用户中心展开，将物品视为被动实体，忽视了其他关键利益相关者的利益。这一局限性加剧了曝光集中度和长尾物品的代表性不足，威胁了系统长期可持续性。在本工作中，我们识别了这一根本局限，并首次提出三方LLM代理推荐框架（TriRec），该框架明确协调了用户效用、物品曝光和平台级公平性。该框架采用两阶段架构：第一阶段赋予物品代理个性化自我推广能力，以提升匹配质量并缓解冷启动障碍；第二阶段执行平台级序列多目标重排序，平衡用户相关性、物品效用和曝光公平性。实验结果表明，在准确性、公平性和物品级效用上均取得了一致提升。此外，我们发现物品自我推广能同时增强公平性和有效性，挑战了相关性与公平性之间传统的权衡假设。我们的代码已开源，见https://github.com/Marfekey/TriRec。