<?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>SWE-Agents on Cognaptus</title>
    <link>https://cognaptus.com/tags/swe-agents/</link>
    <description>Recent content in SWE-Agents on Cognaptus</description>
    <generator>Hugo -- 0.145.0</generator>
    <language>en-us</language>
    <lastBuildDate>Tue, 22 Sep 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://cognaptus.com/tags/swe-agents/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>The Benchmark Is in the Trace: Reusing Agent Trajectories to Shrink SWE Evaluation</title>
      <link>https://cognaptus.com/blog/2026-09-22-the-benchmark-is-in-the-trace-reusing-agent-trajectories-to-shrink-swe-evaluation/</link>
      <pubDate>Tue, 22 Sep 2026 00:00:00 +0000</pubDate>
      <guid>https://cognaptus.com/blog/2026-09-22-the-benchmark-is-in-the-trace-reusing-agent-trajectories-to-shrink-swe-evaluation/</guid>
      <description>PTA-IRT shows how historical agent trajectories can help smaller SWE-agent evaluation subsets preserve full-benchmark scores and rankings.</description>
    </item>
  </channel>
</rss>
