# Simia-Agent-Training

**Repository Path**: mirrors_microsoft/Simia-Agent-Training

## Basic Information

- **Project Name**: Simia-Agent-Training
- **Description**: Official Implementation of "Simulating Environments with Reasoning Models for Agent Training"
- **Primary Language**: Unknown
- **License**: MIT
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2025-11-16
- **Last Updated**: 2026-01-31

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# Simulated Environemnt for Agent Training 

This repository contains the code implementation for the paper: [Simulating Environments with Reasoning Models for Agent Training](https://arxiv.org/abs/2511.01824).

## Repository Structure

- **Simia_SFT/**: Supervised Fine-Tuning (SFT) pipeline
  - Simulated trajectories synthetic pipline for SFT training


- **Simia-RL/**: Reinforcement Learning (RL) framework
  - RL training framework on the simulated environment


## Quick Start

### SFT Pipeline
Navigate to `Simia_SFT/` for more information.

### RL Framework
Navigate to `Simia-RL/` for more information.

### Eval
Navigate to `tau2-bench/` and `OfficeBench/` for more information.

---