Nace AI有发布 Drex for Search，带来的Drex决定模型用于文档搜索。 Drex for Search是帮助人们和agents找到证据的检索层。 编码agents如Claude Code,Codex,Cursor和OpenCode通过CLI,SDKs,MCP或REST将其取名。 在Nace的评价中，它在用GPT-5的浏览器Comp-Plus上得分92.05%，每个问题使用12.6个搜索电话。
TL; DR 数据
- 大小：一个主机搜索系统，用于搜索超过1M+的文件。 它与GPT-5,Gemini 3.5 Flash或Qwen 27B等应答模型相配。
- 运行在：Nace管理云、专用云、你自己的AWS或Azure账户，或Prem上和空出。
- 表现：在4个公共领导板中的3个上排名第1或第2名，按Nace计算。
- 最佳：77.5% R@1在VisDocAgent Bench上，比Claude Opus 5(67.5%)高10分。
Nace AI发布了什么？
Nace AI帧搜索作为一系列决定。 Drex for Search将Drex模型应用于这些决定。 Drex 得分给定选项，每个选项有校准概率，在1个前传。 这使得每agent步都足够便宜。
发行目标为经典的RAG,Nace将其概括为"块","嵌入","上-克","希望".
3起输油管中断：
- 答案放在第23页的桌子上
- 答案需要两个跳出文件
- 答案在扫描的PDF里
agent内部的搜索工作Drex如何进行？.
Nace描述了三个步骤：
- 分类：在任何搜索运行之前，Drex会决定问题是否需要快速检查或agent. agent路由读取文件和查询表。
- squeeze: Drex按级别行走工作空间级别：文件夹，文件，部分，页。 在一个表里，它缩小到桌子和柱子。 每一个关卡都只保留能持有答案的东西。
- 答复：只有保存的页和表格达到LLM。 答案引用了文件和页面。
深度是固定的，因此Nace 称一百万个文件采取与一千个一样多的步骤。
它能帮助编码 agents多少？
Nace AI在OfficeQA Pro上测试了9个agent和型号配对，一个133个问题基准测试超过美国财政部公告。 主要亮点：回答正确度增加6%，步骤减少62%，代币减少56%，速度加快2.3x.
工作空间包括什么？
- 文件：PDF和扫描、xlsx、csv和Parquet、mp3和mp4、docx、pptx、md、json和txt。
- 引用：每个回答名称文件和页面，行或分钟它来自。
- 工作空间：与世隔绝，有自己的索引和知识图，可与受邀成员分享。
- 存储：上传文件或文件夹，或在自己的S3桶或Azure Blob容器中保留工作空间。
- 零保留：可自存。
- 领域：税务、并购、SEC 10-K、合同或你自己。
它在浏览器Comp-Plus上的表现如何？
浏览Comp-Plus在大约100K个固定的网页文档中询问一个深层研究的agent 830多跳问题。 GPT-5的Nace AI报告：
- 92.05%的准确度，领导板上86个条目中的第2个。
- 每问12.61次查询电话，比前方唯一一次(209.27次)减少16.6x。
- 87.32%的通行证，有8.93个搜索电话，是10个电话以下的最好条目。
- Qwen3-Embed-8B基线上方的+20.4分，同为GPT-5型号。
在基准测试文档上得分如何？
在VisDocAgent Bench上，在2,375 arXiv页中，agent 发现 1目标页。 Drex for Search的得分为77.5% R@1，使用开放式Qwen 27B计划车。 最佳发布agent,Claude Opus 5分67.5%. R@1在直接题上为97.5%，一桥上为77.5%，二桥上为57.5%.
在MADQA上，agents回答超过800个PDF并引用页面。 Nace报告精度94.7%，使用Gemini 3.5 Flash和分页F1的88.2. 它的功率校正(Kuiper)为6.66. Nace根据10月20日读取的"领跑板"将其排名为#1. 以开放重量的Qwen 27B,Nace报告为93.4%.
在EntertainmentRAG-Bench上，拥有50万+公司内部文件，Nace报告的总分为88.22分，排名为#3. 即OpenAI文件搜索(61.03)上面的27.2分。
它如何与最佳公布结果进行比较？
分数和分数均由Nace AI发布，取自领跑板于2026年10月20日阅览。
开发者如何获得访问权限？.
Drex for Search在 Nace API Console 中运行，一个键上有4个方式：
-CLI:PyPI上的nace-cli.
- SDKs：用于Python的Nace-sdk和用于TypeScript的Nace-sdk.
- MCP:nace-mcp，用于Claude Code,Codex,Cursor或OpenCode.
- 一个OpenAPI规格。
关键外卖
- Drex for Search 给出了 agents 引用的页面和表格，而不是上克块。
- 92.05%在浏览器Comp-Plus上，搜索电话比前面唯一一个条目少了16.6%。
- 7.5% R@1在维斯道克特奔驰，比Claude Opus 5.
- 在OfficeQA Pro上，agent转弯，所有9个牵引和模型对纳斯测试。
请检查dex的搜索页面，API Console,Docs和Hugging Face.
感谢Nace AI团队为这篇文章提供的思想领导/资源。 这篇文章由Nace AI赞助。
Asif Razzaq是Marktechpost AI Media Inc.的首席执行官。 作为一个有远见的企业家和工程师，阿西夫致力于利用人工智能的潜力为社会造福。 他最近的努力是人工智能媒体平台的发布，该平台以深入报道机器学习和深层学习新闻而出名，这些新闻在技术上既可靠又为广大观众所容易理解。 该平台每月有超过200万次观看，表明其受观众欢迎。
本文由 AI宝库自动抓取并翻译，版权归原作者所有；如需查看原文请点下方链接。
Nace AI has released Drex for Search, which brings its Drex decision models to document search. Drex for Search is a retrieval layer that helps people and agents find evidence. Coding agents such as Claude Code, Codex, Cursor and OpenCode call it through CLI, SDKs, MCP or REST. In Nace’s evaluation, it scores 92.05% on BrowseComp-Plus with GPT-5, using 12.6 search calls per question.
TL;DR
- Size: a hosted search system built to search over 1M+ files. It pairs with an answering model such as GPT-5, Gemini 3.5 Flash or Qwen 27B.
- Runs on: Nace’s managed cloud, a dedicated cloud, your own AWS or Azure account, or on-prem and air-gapped.
- Performance: ranked #1 or #2 on 3 of 4 public leaderboards, per Nace.
- Best: 77.5% R@1 on VisDocAgentBench, 10 points above Claude Opus 5 (67.5%).
What did Nace AI release?
Nace AI frames search as a series of decisions. Drex for Search applies its Drex models to those decisions. Drex scores given options with a calibrated probability each, in 1 forward pass. That makes it cheap enough for every agent step.
The release targets classic RAG, which Nace sums up as chunk, embed, top-k, hope.
The pipeline breaks in 3 cases:
- the answer sits in a table on page 23
- the answer needs 2 hops across files
- the answer is inside a scanned PDF
How does Drex for Search work inside an agent?
Nace describes 3 steps:
- Classify: Before any search runs, Drex decides if the question needs a quick lookup or an agent. The agent route reads documents and queries tables.
- Squeeze: Drex walks the workspace level by level: folder, file, section, page. Inside a sheet, it narrows to table and column. Each level keeps only what can hold the answer.
- Answer: Only the kept pages and tables reach the LLM. The answer cites the file and page.
Depth is fixed, so Nace says a million files take as many steps as a thousand.
How much does it help coding agents?
Nace AI tested 9 agent and model pairs on OfficeQA Pro, a 133-question benchmark over U.S. Treasury Bulletins. Key highlights: 6% more answers right, 62% fewer steps, 56% fewer tokens, and 2.3x faster.
What does a workspace include?
- Files: PDFs and scans, xlsx, csv and Parquet, mp3 and mp4, docx, pptx, md, json and txt.
- Citations: every answer names the file and the page, row or minute it came from.
- Workspaces: isolated, with their own index and knowledge graph, and shareable with invited members.
- Storage: upload files or folders, or keep workspaces in your own S3 bucket or Azure Blob container.
- Zero retention: available with your own storage.
- Domains: Tax, M&A, SEC 10-K, Contracts, or your own.
How does it perform on BrowseComp-Plus?
BrowseComp-Plus asks a deep-research agent 830 multi-hop questions over about 100K fixed web documents. With GPT-5, Nace AI reports:
- 92.05% accuracy, #2 of 86 entries on the leaderboard.
- 12.61 search calls per question, 16.6x fewer than the only entry ahead (209.27 calls).
- 87.32% in a single pass with 8.93 search calls, the best of any entry under 10 calls.
- +20.4 points over the Qwen3-Embed-8B baseline, with the same GPT-5 model.
How does it score on document benchmarks?
On VisDocAgentBench, an agent finds 1 target page among 2,375 arXiv pages. Drex for Search scores 77.5% R@1 with an open-weight Qwen 27B planner. The best published agent, Claude Opus 5, scores 67.5%. R@1 is 97.5% on direct questions, 77.5% on one bridge, and 57.5% on two.
On MADQA, agents answer over 800 PDFs and cite pages. Nace reports 94.7% accuracy with Gemini 3.5 Flash and a page-attribution F1 of 88.2. Its effort calibration (Kuiper) is 6.66. Nace ranks it #1, based on the leaderboard as read on October 20. With open-weight Qwen 27B, Nace reports 93.4%.
On EnterpriseRAG-Bench, with 500,000+ internal company documents, Nace reports an overall score of 88.22, which it ranks #3. That is 27.2 points above OpenAI File Search (61.03).
How does it compare with the best published results?
Ranks and scores are as published by Nace AI, from leaderboards read October 20, 2026.
How can developers get access?
Drex for Search runs in the Nace API Console, with 4 ways in on one key:
- CLI: nace-cli on PyPI.
- SDKs: nace-sdk for Python and nace-sdk for TypeScript.
- MCP: nace-mcp, for Claude Code, Codex, Cursor or OpenCode.
- REST: an OpenAPI spec.
Key Takeaways
- Drex for Search gives agents cited pages and tables, not top-k chunks.
- 92.05% on BrowseComp-Plus with 16.6x fewer search calls than the only entry ahead.
- 77.5% R@1 on VisDocAgentBench, 10 points above Claude Opus 5.
- On OfficeQA Pro, agent turns fell for all 9 harness and model pairs Nace tested.
Check out the Drex for Search page, API Console, Docs and Hugging Face.
Thanks to the Nace AI team for the thought leadership / resources for this article. This article is sponsored by Nace AI.
Asif Razzaq is the CEO of Marktechpost AI Media Inc.. As a visionary entrepreneur and engineer, Asif is committed to harnessing the potential of Artificial Intelligence for social good. His most recent endeavor is the launch of an Artificial Intelligence Media Platform, Marktechpost, which stands out for its in-depth coverage of machine learning and deep learning news that is both technically sound and easily understandable by a wide audience. The platform boasts of over 2 million monthly views, illustrating its popularity among audiences.
Auto-fetched and translated by AI Gem Box. All rights belong to the original author.