小模型也能选工具且可迁移：Meta/CMU Zanette，8B 41.5% > Maverick 30.6%
小模型也能选工具且可迁移：Meta/CMU Zanette，8B 41.5% > Maverick 30.6%
View PDF HTML (experimental) Abstract: As LLM agents operate over corpora of more than ten thousand tools, selecting the right tool for a complex multi-step user instruction becomes a central bottleneck. Tool descriptions cannot all fit in context, and relevance-based...
Meta/CMU Zanette 模型 (arXiv:2610.31483)
“View PDF HTML (experimental) Abstract: As LLM agents operate over corpora of more than ten thousand tools, selecting the right tool for a co”
Abstract:As LLM agents operate over corpora of more than ten thousand tools, selecting the right tool for a complex multi-step user instruction becomes a central bottleneck. Tool descriptions cannot all fit in context, and relevance-based retrievers only rank tools without knowing which are actually needed. Recent work instead leverages proprietary commercial LLMs like Claude or ChatGPT to drive a retriever, decomposing the instruction and selecting over retrieved candidates. We show that a small, open model can be trained via reinforcement learning to perform the same functionality. On ToolBench, a Qwen3-8B model post-trained with our recipe outperforms Llama-4-Maverick (402B). In addition, the trained model transfers directly to different retrievers and generalizes to new tool corpora in different domains.
| Comments: | 19 pages, 5 figures, 5 tables |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.31483 [cs.LG] |
| (or arXiv:2610.31483v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.31483 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zhaoyi Zhou [view email]
[v1]
Thu, 22 Oct 2026 16:07:49 UTC (190 KB)
Source: Agent Control Flash News · arxiv.org
Related Products & Analysis
Cursor Agent 架构全景拆解：从影子工作区到多文件推演引擎
全面剖析 Cursor 在 Agent 模式下的底层技术实现，解析影子分支隔离、LSP 上下文剪枝以及预测性补全的核心架构细节与工程实践经验。
Vercel v0 推出全新多 Agent 协作画布与实时全栈部署预览
动态速评：v0 正在从单一组件生成器演进为全栈应用搭建协作台，尤其是与 Neon/Postgres 的直连极大降低了全栈原型验证成本。