<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>LLM Agents | Zunzhe Zhang</title><link>https://tuagoale.github.io/tags/llm-agents/</link><atom:link href="https://tuagoale.github.io/tags/llm-agents/index.xml" rel="self" type="application/rss+xml"/><description>LLM Agents</description><generator>HugoBlox Kit (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Mon, 30 Jun 2025 00:00:00 +0000</lastBuildDate><image><url>https://tuagoale.github.io/media/icon.svg</url><title>LLM Agents</title><link>https://tuagoale.github.io/tags/llm-agents/</link></image><item><title>Ella: Embodied Social Agents with Lifelong Memory</title><link>https://tuagoale.github.io/publications/ella/</link><pubDate>Mon, 30 Jun 2025 00:00:00 +0000</pubDate><guid>https://tuagoale.github.io/publications/ella/</guid><description>&lt;p&gt;Ella focuses on long-horizon embodied social behavior: agents must observe, remember, plan, and interact across days rather than solve isolated tasks. Its memory system organizes acquired knowledge in semantic form while preserving episodic traces of multimodal experience.&lt;/p&gt;
&lt;p&gt;The system is evaluated in a dynamic 3D open world where multiple agents participate in social activities and are later tested on controlled tasks such as influence, leadership, and cooperation. The results show how structured memory can help foundation-model agents learn from observation and interaction.&lt;/p&gt;</description></item><item><title>LLM-Enhanced RPG Game with Context-Aware NPC Agents</title><link>https://tuagoale.github.io/projects/llm-rpg-agents/</link><pubDate>Sat, 01 Jun 2024 00:00:00 +0000</pubDate><guid>https://tuagoale.github.io/projects/llm-rpg-agents/</guid><description>&lt;p&gt;Built an LLM-driven RPG prototype using GPT-4o and RPG Maker to enable context-aware NPC dialogue generation.&lt;/p&gt;
&lt;p&gt;Designed prompt templates and game-state interfaces that allowed NPCs to condition responses on player progress, dialogue history, and task context. The project explored adaptive response generation and interactive narrative control.&lt;/p&gt;</description></item></channel></rss>