LLM Agents and Applications
LLM agents for tool use, user simulation, education, medicine, finance, speech interaction, and micro-world environments.
This project organizes papers where LLMs do more than answer: they plan with tools, simulate users, play roles, teach learners, act as standardized patients, participate in markets, or operate inside evolving environments.
Research Storyline
Smurfs studies how multiple agents can coordinate tool planning while keeping search context efficient.
UserGPT and PlatoLM turn LLMs into simulated users, giving dialogue systems richer multi-turn practice.
EasyMED and AI standardized patients make clinical communication and reasoning practice repeatable and measurable.
TwinMarket and MicroVerse move from isolated prompts to environments where agent actions change future states.
Paper Trail
Uses multi-agent search for tool planning with better context efficiency.
PaperBuilds LLM user simulators for dialogue data generation, training, and evaluation.
PaperUses Socratic user simulation to improve multi-turn dialogue learning.
PaperCompares AI standardized patients and human standardized patients for medical education.
PaperOptimizes role-playing agents while preserving character fidelity and reasoning quality.
PaperSimulates financial markets with LLM investor agents that carry beliefs, desires, intentions, and actions.
Project pageExplores scientific micro-world simulation with hidden mechanisms and evolving states.
Project pageApplication Clusters
Smurfs organizes tool planning as a multi-agent search problem rather than a single fragile ReAct trajectory.
User simulators, PlatoLM, and AI standardized patients use interaction to create practice, feedback, and evaluation loops.
CRPO studies how RL objectives should change when the agent must preserve persona, style, and character consistency.
TwinMarket, Economic World Models, and MicroVerse treat agents as actors inside environments that respond to their decisions.
Resource Map
Paper and ACL Anthology page for multi-agent tool planning.
PaperAI standardized patient framework and medical education evaluation resources.
RepositoryFinancial market simulation with LLM investor agents.
Project pageMicro-world simulation for scientific environments.
Project page