CLMM
Manage concentrated liquidity and inventory risk in a market with liquidity-dependent price impact.
Resources
Practice locally
Download the standalone simulator and starter. Install NumPy and Gymnasium in a virtual environment, then run your strategy against the public practice seeds.
python3 -m venv .venv .venv/bin/python -m pip install -e . .venv/bin/python -m clmm_challenge.evaluate --agent submission_template.py
Run these commands inside the extracted clmm-challenge directory. Only run your own trusted strategy files locally.
Uniswap v3 Whitepaper
The protocol design behind concentrated liquidity — ranges, ticks, and fee accrual.
uniswap.org · PDF
SAiFE-gym: Model-based Environments for Automated Market Making with Concentrated Liquidity
The SAiFE-gym manuscript describing the research framework behind this challenge, including concentrated-liquidity simulation environments and dynamic liquidity provision.
arxiv.org · arXiv:2609.17788
Concentrated Liquidity Provision: a Reinforcement Learning Perspective
Reinforcement learning for choosing liquidity ranges and rebalancing positions, accounting for inventory risk, market uncertainty, and rebalancing costs.
arxiv.org · arXiv:2608.19389