<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Llm-Panel — OHLCV</title><link>https://ohlcv.io/tags/llm-panel/</link><description>Quant trading research and writing</description><generator>Hugo</generator><language>en-au</language><lastBuildDate>Sun, 12 Jul 2026 01:44:51 +1000</lastBuildDate><atom:link href="https://ohlcv.io/tags/llm-panel/" rel="self" type="application/rss+xml"/><item><title>From papers to positions: what four AI models found reading 468 academic studies</title><link>https://ohlcv.io/posts/llm-panel-academic-review/</link><pubDate>Sun, 12 Jul 2026 00:00:00 +1000</pubDate><guid>https://ohlcv.io/posts/llm-panel-academic-review/</guid><description>A blind panel of four frontier language models each read 468 academic trading papers and independently converged on the same short list of futures-tradable ideas. This sets out what they agreed on, where they split, and what survived an adversarial fact-check.</description></item></channel></rss>