Memory Intelligence Agent
Paper • 2604.04503 • Published • 58
How to use from
SGLangUse Docker images
docker run --gpus all \
--shm-size 32g \
-p 30000:30000 \
-v ~/.cache/huggingface:/root/.cache/huggingface \
--env "HF_TOKEN=<secret>" \
--ipc=host \
lmsysorg/sglang:latest \
python3 -m sglang.launch_server \
--model-path "LightningCreeper/MIA" \
--host 0.0.0.0 \
--port 30000# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "LightningCreeper/MIA",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'Quick Links
Memory Intelligence Agent (MIA)
Memory Intelligence Agent (MIA) is a memory framework designed for deep research agents (DRAs). It transforms agents from "passive record-keepers" into "active strategists" using a sophisticated Manager-Planner-Executor architecture.
- Paper: Memory Intelligence Agent
- Repository: https://github.com/ECNU-SII/MIA
Overview
MIA replaces traditional "memory dumps" with a specialized architecture to enable efficient reasoning and autonomous evolution:
- The Manager: A non-parametric memory system that stores and optimizes compressed historical search trajectories to eliminate bloat.
- The Planner: A parametric memory agent that produces search plans and evolves its strategy via Continual Test-Time Learning during inference.
- The Executor: A precision instrument that searches and analyzes information guided by the search plan.
MIA employs an alternating reinforcement learning paradigm to enhance cooperation between components and establishes a bidirectional conversion loop between parametric and non-parametric memories.
Citation
@article{qiao2026mia,
title={Memory Intelligence Agent},
author={Jingyang Qiao and Weicheng Meng and Yu Cheng and Zhihang Lin and Zhizhong Zhang and Xin Tan and Jingyu Gong and Kun Shao and Yuan Xie},
journal={arXiv preprint arXiv:2604.04503},
year={2026}
}
Model tree for LightningCreeper/MIA
Base model
Qwen/Qwen2.5-VL-7B-Instruct
Install from pip and serve model
# Install SGLang from pip: pip install sglang# Start the SGLang server: python3 -m sglang.launch_server \ --model-path "LightningCreeper/MIA" \ --host 0.0.0.0 \ --port 30000# Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "LightningCreeper/MIA", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'