<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>Spreadsheet on Banghao&#39;s Blog</title>
    <link>https://biboyqg.github.io/blog/tags/spreadsheet/</link>
    <description>Recent content in Spreadsheet on Banghao&#39;s Blog</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en-us</language>
    <lastBuildDate>Sat, 06 Jun 2026 03:59:00 -0500</lastBuildDate>
    <atom:link href="https://biboyqg.github.io/blog/tags/spreadsheet/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Spreadsheet-RL: Training Spreadsheet Agents with Real Excel and Reinforcement Learning</title>
      <link>https://biboyqg.github.io/blog/blog/spreadsheet-rl/</link>
      <pubDate>Sat, 06 Jun 2026 03:59:00 -0500</pubDate>
      <guid>https://biboyqg.github.io/blog/blog/spreadsheet-rl/</guid>
      <description>Paper / Project page / Code / Dataset / Model
Spreadsheet software is one of the most ordinary, durable, and quietly difficult interfaces in computing. A spreadsheet can be a small personal budget, a messy monthly close workbook, an investment-banking model, a sales report, a supply-chain planning sheet, or a hand-built database that has survived for years because it works just well enough. That makes spreadsheets a natural target for AI agents: many people would like to say what they want, let the system edit the workbook, and receive a correct final file.</description>
    </item>
  </channel>
</rss>
