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 uses a platform agent for sequential multi-objective re-ranking, balancing user relevance, item utility, and exposure fairness. Experiments on multiple benchmarks 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：大型语言模型（LLM）的最新进展激发了人们对基于智能体的推荐系统日益增长的兴趣，该系统通过语言驱动的交互与推理实现了更具表现力的偏好建模。然而，现有的大多数智能体方法仍主要以用户为中心，将物品视为被动实体，并忽视了其他关键利益相关方的利益。这种局限性加剧了曝光集中和长尾物品代表性不足的问题，威胁着系统的长期可持续性。在本研究中，我们指出了这一根本性局限，并提出了首个三方LLM智能体推荐框架（TriRec），该框架明确协调用户效用、物品曝光和平台层面的公平性。该框架采用两阶段架构：阶段1赋予物品智能体个性化的自我推广能力，以提升匹配质量并缓解冷启动障碍；而阶段2则利用平台智能体进行序列化多目标重排序，以平衡用户相关性、物品效用和曝光公平性。在多个基准数据集上的实验表明，该框架在准确性、公平性和物品级效用方面均取得了一致的提升。此外，我们发现物品的自我推广能够同时增强公平性与有效性，这对传统上认为相关性与公平性之间存在权衡的假设提出了挑战。我们的代码可在 https://github.com/Marfekey/TriRec 获取。