RATED：基于执行动态的可靠性感知工具检索框架
RATED: Reliability-Aware AI Agent Tool Retrieval via Execution Dynamics
智能体调工具经常踩到挂掉的 API，这篇论文用 bandit 实时重排工具候选，把故障率从 86% 压到 3%，还附带了 21 万对的评测数据集。
论文提出 RATED 框架，用冻结双编码器加对比微调做语义匹配，再用轻量 contextual bandit 模块根据实时执行反馈重排候选工具。作者同时发布 EcoAgent 基准，包含 5,172 个真实工具和超过 21 万条查询-工具对。在真实查询上，RATED 的 MRR 相比 ToolLLM API 检索器提升 52.2%。在 30% 故障率的 API 中断场景下，故障选择率从 86.2% 降至 2.9%，额外延迟低于 1 ms。代码和数据集已在 GitHub 开源。
RATED: Reliability-Aware AI Agent Tool Retrieval via Execution Dynamics
As AI agents increasingly rely on external tools, accurate retrieval is essential for reliable behavior. Existing methods optimize semantic relevance but largely ignore tool availability during execution. To address this gap, we propose RATED (Reliability-Aware Tool Retrieval via Execution Dynamics), a retrieval framework that combines robust semantic matching with dynamic reliability adaptation. RATED employs a frozen dual-encoder with contrastive fine-tuning for semantic matching, and a lightweight contextual bandit module that re-ranks candidates based on real-time execution feedback. This design enables rapid adaptation to runtime tool failures without expensive model retraining. We introduce EcoAgent, a benchmark of 5,172 real-world tools and over 210,000 query-tool pairs for offline retrieval and dynamic reliability evaluation. Experimental results demonstrate that RATED achieves a 52.2% relative MRR improvement over the ToolLLM API retriever on real-world queries, and reduces fault selection rate from 86.2% to 2.9% under severe API outage scenarios with a 30% failure rate, while incurring negligible latency overhead of less than 1 ms over encode-only inference. The code and dataset are available at https://github.com/Elliotes/EcoAgent.
