Files
myWiki/raw/papers/gaurav-dynamic-react-2025.md

54 lines
2.1 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

---
title: "Dynamic ReAct: Scalable Tool Selection for Large-Scale MCP Environments"
created: 2026-06-19
updated: 2026-06-19
type: paper-raw
source: https://arxiv.org/abs/2509.20386
arxiv_id: 2509.20386
version: v1
---
# Dynamic ReAct: Scalable Tool Selection for Large-Scale MCP Environments
**Authors**: Nishant Gaurav, Adit Akarsh, Ankit Ranjan, Manoj Bajaj (agentr.dev)
**Published**: 2025-09-22
**Venue**: arXiv:2509.20386 (cs.SE, cs.AI, cs.IR)
## 核心问题
当 MCP 工具生态扩展到数百到数千个工具时,传统 ReAct Agent 的全量加载方式不可行——LLM 上下文有硬限制。
## 五架构演进
### 1. Baseline: Direct Semantic Search
用户查询直接入向量库 → 取 top-k → 绑定 LLM。简单但噪声严重"退订链接"查询返回 Mailchimp 的 unsubscribe 报告而非 Gmail 工具)。
### 2. Meta-Tool Query Construction
暴露向量搜索为 meta-toolLLM 先构造原子化搜索查询再检索。更精确,但仍需大 k 值。
### 3. Search and Load★ 最优)
两个 meta-tool`search_tools`两级搜索k1=20→去重→每应用上限 k2=5+ `load_tools`LLM 精选后显式加载)。多查询合并、精确加载 < 5 个工具
### 4. Application-Aware (Hierarchical Search)
增加 `search_apps` 先定位应用再搜工具application filtering 在语义搜索中效果有限——LLM 倾向直接用 query 包含 app
### 5. Fixed Tool Set
四个固定 meta-tool 动态获取工具信息并调用缓存效率好但长对话中性能退化
## 向量检索优化
| 策略 | Top-5 | Top-10 |
|------|-------|--------|
| OpenAI text-embedding-3-large (baseline) | 40% | 64% |
| voyage-context-3 | 48% | 68% |
| **voyage-context-3 + Sonnet context enrichment** | **60%** | 68% |
| + BM25 hybrid | 56% | 72% |
Context enrichment 带来 50% 相对提升Top-5: 4060%)。
## 关键创新
- **default tools**create_table + web_search 始终可用避免为通用任务浪费搜索
- **Meta-tool 作为"七杠杆"**LLM Client (1) + Meta Tools (4) + Tool Registry (1) + Vector DB (1)
- 工具加载减少 **50%**准确率不降