ModelsMulti-source

Amazon-Web-Search-Agent 登顶 Search Arena

Why we picked it

Amazon 把自家后训练模型和 AgentCore Web Search 打包成搜索智能体,在用户盲测里投出了全场第一。做联网问答或搜索类智能体的开发者可以看看,托管搜索管道比自己拼 RAG 省事,排名也是真实投票出来的。

Amazon 的 Amazon-Web-Search-Agent 搭配 AgentCore Web Search,在 Search Arena 排行榜上拿下第一。

Body

该组合属于 Amazon 定制的搜索智能体方案,结合了自家后训练模型与网页搜索工具,用于联网检索类任务。Search Arena 是 LMArena 旗下对比模型联网搜索能力的公开评测榜单,通过用户盲测投票排序,登顶意味着其在真实查询中优于同榜单其他搜索模型组合。

对开发者而言,AgentCore 提供的托管网页搜索能力可直接接入智能体工作流,与自建 RAG 检索方案相比省去维护搜索管道的成本。这一成绩也反映出云厂商正把搜索型智能体作为与 OpenAI、Perplexity 等对手竞争的切入点。

Original · lmarena.ai

Amazon’s model, Amazon-Web-Search-Agent coupled with AgentCore Web Search, takes the #1 spot on Search Arena! Congrats to the @Amazon team on this release! Learn more about their custom post-trained models in thread.📊 32 ⚡

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Models" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Amazon, AgentCore, Search Arena, agents.

Source attribution: curated from lmarena.ai (@lmarena_ai). Cross-source corroboration: 11 independent sources have covered this development (including Perplexity, Aravind Srinivas, Yuchen Jin), confirming industry-wide signal strength.