按年被提到
20252025 · 2 次2026
强化学习与智能体›大模型智能体·arXiv:2511.21689 · cs.CL

ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration

Hongjin Su, Shizhe Diao, Ximing Lu, Mingjie Liu, Jiacheng Xu, Xin Dong, Yonggan Fu, Peter Belcak, Hanrong Ye, Hongxu Yin, Yi Dong, Evelina Bakhturina 等 16 人 · 2025
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 3 人首次 2025-11-27 · 最近 2026-08-11
3不同的人
2活跃月份
3讨论串
4被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Large language models are powerful generalists, yet solving deep and complex problems such as those of the Humanity's Last Exam (HLE) remains both conceptually challenging and computationally expensive. We show that small orchestrators managing other models and a variety of tools can both push the upper bound of intelligence and improve efficiency in solving difficult agentic tasks. We introduce ToolOrchestra, a method for training small orchestrators that coordinate intelligent tools. ToolOrchestra explicitly uses reinforcement learning with outcome-, efficiency-, and user-preference-aware rewards. Using ToolOrchestra, we produce Orchestrator, an 8B model that achieves higher accuracy at lower cost than previous tool-use agents while aligning with user preferences on which tools are to be used for a given query. On HLE, Orchestrator achieves a score of 37.1%, outperforming GPT-5 (35.1%) while being 2.5x more efficient. On tau2-Bench and FRAMES, Orchestrator surpasses GPT-5 by a wide margin while using only about 30% of the cost. Extensive analysis shows that Orchestrator achieves the best trade-off between performance and cost under multiple metrics, and generalizes robustly to unseen tools. These results demonstrate that composing diverse tools with a lightweight orchestration model is both more efficient and more effective than existing methods, paving the way for practical and scalable tool-augmented reasoning systems.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论Foreskin_Mafia · 2026-08

“> Local models are more expensive and less efficient > Local models are never going to be as powerful. Proven wrong empirically by Nvidia back in November: https://arxiv.org/abs/2511.21689 "On HLE, Orchestrator achieves a score of 37.1%, outperforming GPT-5 (35.1%) while being 2.5x more efficient." Cute blog though”

Local Models Will Not Win原评论 ↗
被提交为 story · 2 次