RecToolBench：模糊意图下推荐专用工具编排基准
原标题：RecToolBench: Benchmarking Recommendation-Specific Tool Orchestration under Fuzzy User Intent
AI 摘要
该论文提出 RecToolBench，一个基于 MCP 的基准测试，用于评估模糊用户指令下推荐智能体的工具编排能力。它包含 1200 多个可执行任务、13 个 MCP 服务器和 32 个工具，覆盖单工具、并行、串行及混合编排四种难度。实验表明，语法正确的工具调用并不保证推荐成功，模型在语义参数落地、多步证据整合和最终推荐上表现不佳，工具编排是智能体推荐系统的主要瓶颈。
正文节选
RecToolBench: Benchmarking Recommendation-Specific Tool Orchestration under Fuzzy User Intent Abstract Recent advances in agentic recommender systems are shifting recommender systems from passive filtering engines to instruction-following agents that use external tools to resolve user intent. However, existing benchmarks often assume explicit user intent, simplified tool environments, or isolated function calls, leaving realistic tool orchestration for recommendation underexplored. To bridge thi