EVAGE: Autonomous MEV Generation and Adaptation via Multi-Agent Harness
EVAGE is a multi-agent system that autonomously generates and adapts MEV bots across Ethereum, Base, and BSC.
EVAGE is a multi-agent research framework that generates and adapts maximal extractable value (MEV) strategies offline so model inference stays off the live execution path. An orchestrator and three subagents implement and repair bot workflows through closed-loop diagnostics, producing deterministic proof-of-concept code. On more than 1.5 million blocks each from Ethereum, Base, and BNB Smart Chain, the authors report five new Ethereum variants with profit increases from 1.02x to 15.97x, adaptation of 11 strategies from CPMM to CLMM and Balancer V2, and ports from Ethereum to Base and BSC for under $60 in token cost.
- EVAGE generates and repairs MEV bot code offline via specialized agents.
- Five new Ethereum strategy variants yielded up to 15.97x reported profit.
- Eleven strategies were adapted across CPMM, CLMM, and Balancer V2.
- Cross-chain ports to Base and BSC cost under $60 in LLM tokens.
From the original article
1 min read at arxiv.orgMaximal Extractable Value (MEV) has evolved into a major economic force in blockchain ecosystems, yet its capture is dominated by experienced teams, and both strategy design and implementation rely on manual expert work that scales poorly across heterogeneous protocols and chains. We present EVAGE, the first fully autonomous multi-agent framework for end-to-end MEV strategy generation and adaptation.
By Yan Wen · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.