<?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>Automated-Proving on Cognaptus</title>
    <link>https://cognaptus.com/tags/automated-proving/</link>
    <description>Recent content in Automated-Proving on Cognaptus</description>
    <generator>Hugo -- 0.145.0</generator>
    <language>en-us</language>
    <lastBuildDate>Wed, 07 Oct 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://cognaptus.com/tags/automated-proving/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>More Proof Machinery, More Compute: What TCSAlgBench Says About Research Agents</title>
      <link>https://cognaptus.com/blog/2026-10-07-more-proof-machinery-more-compute-what-tcsalgbench-says-about-research-agents/</link>
      <pubDate>Wed, 07 Oct 2026 00:00:00 +0000</pubDate>
      <guid>https://cognaptus.com/blog/2026-10-07-more-proof-machinery-more-compute-what-tcsalgbench-says-about-research-agents/</guid>
      <description>TCSAlgBench shows that structured proof-agent workflows can expand research-level theorem coverage, but the gains come with uneven success patterns and sharply different inference costs.</description>
    </item>
  </channel>
</rss>
