<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>The Elixirs Lab — Research</title><description>Notes and findings from work in progress. Quantitative finance, ML systems, and the engineering challenges that come with both.</description><link>https://theelixirslab.com/</link><language>en-us</language><item><title>PAPER 003 — Latency budgets for production RAG</title><link>https://theelixirslab.com/research/rag-latency/</link><guid isPermaLink="true">https://theelixirslab.com/research/rag-latency/</guid><description>Lessons from architecting a RAG system serving 10M+ daily requests. How to reason about end-to-end latency, what to optimize first, and where the surprising bottlenecks usually are.</description><pubDate>Wed, 01 Jul 2026 00:00:00 GMT</pubDate><category>Infrastructure</category><category>ML systems</category></item><item><title>PAPER 002 — Reward hacking patterns in LLM agent benchmarks</title><link>https://theelixirslab.com/research/reward-hacking/</link><guid isPermaLink="true">https://theelixirslab.com/research/reward-hacking/</guid><description>Cataloging reward-hacking strategies observed across 200+ trajectory annotations on Terminal-Bench. We propose a taxonomy and recommend evaluation patterns that resist gaming.</description><pubDate>Mon, 01 Jun 2026 00:00:00 GMT</pubDate><category>Evaluation</category><category>ML systems</category></item><item><title>PAPER 001 — Regime detection in illiquid frontier markets</title><link>https://theelixirslab.com/research/regime-detection/</link><guid isPermaLink="true">https://theelixirslab.com/research/regime-detection/</guid><description>We propose a Hidden Markov Model approach to detect regime shifts in markets where standard volatility-clustering signals are unreliable due to thin trading. Tested across NGX, NSE, and BVMW.</description><pubDate>Fri, 15 May 2026 00:00:00 GMT</pubDate><category>Quant</category><category>Time series</category></item></channel></rss>