<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Theory-of-Mind(ToM) | Shaoyang Cui</title><link>https://spidermonk7.github.io/tags/theory-of-mindtom/</link><atom:link href="https://spidermonk7.github.io/tags/theory-of-mindtom/index.xml" rel="self" type="application/rss+xml"/><description>Theory-of-Mind(ToM)</description><generator>Hugo Blox Builder (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Mon, 01 Dec 2025 00:00:00 +0000</lastBuildDate><image><url>https://spidermonk7.github.io/media/icon_hu7729264130191091259.png</url><title>Theory-of-Mind(ToM)</title><link>https://spidermonk7.github.io/tags/theory-of-mindtom/</link></image><item><title>TradeCraft - Exploring Theory of Mind in LLM Agents' Strategic Decision-Making and Communication</title><link>https://spidermonk7.github.io/ongoing-projects/tradecraft/</link><pubDate>Mon, 01 Dec 2025 00:00:00 +0000</pubDate><guid>https://spidermonk7.github.io/ongoing-projects/tradecraft/</guid><description>&lt;p>LLM agents’ reliance on implicit Theory of Mind (ToM) during strategic decision-making remains debated. We investigate this using a Minecraft-inspired &amp;ldquo;trade-and-craft&amp;rdquo; game requiring goal inference and item exchange. By augmenting agents with explicit ToM scaffolding—where players report multi-order beliefs about opponents—we evaluate the alignment between inferred mental states and behavioral outcomes.&lt;/p>
&lt;!-- Official page: &lt;https://tradecraft26.github.io> -->
&lt;!-- Repository: &lt;https://github.com/spidermonk7/tradecraft> --></description></item></channel></rss>