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 $60 in LLM tokens.
Full article209 words · extracted from arxiv.org · click to collapse
Maximal Extractable Value (MEV) has evolved into a major economic force in blockchain ecosystems, yet its capture is dominated by experienced teams, and both strategy design and implementation rely on manual expert work that scales poorly across heterogeneous protocols and chains. We present EVAGE, the first fully autonomous multi-agent framework for end-to-end MEV strategy generation and adaptation. Equipped with three specialized operation modes, it automatically discovers novel MEV variants, adapts execution logic across disparate protocols, and ports strategies between chains, including Layer-1 and Layer-2 networks. To avoid inference latency on the critical MEV execution path, EVAGE generates and refines MEV bot code offline rather than making real-time decisions directly. Under the coordination of an orchestrator agent, three specialized subagents collectively implement and repair the full MEV bot workflow via closed-loop diagnostics, eliminating human intervention while producing validated and deterministic Proof-of-Concept implementations. We evaluate EVAGE on over 1.5M blocks from each of Ethereum, Base, and BNB Smart Chain (BSC). On Ethereum, EVAGE uncovers five novel MEV strategy variants, yielding a profit increase of 1.02$\times$ to 15.97$\times$. It also successfully adapts 11 MEV strategies from CPMM to both CLMM and Balancer V2 and ports strategies from Ethereum to Base and BSC, all with less than 60 dollars in LLM token costs.
Text extracted automatically; images, tables and formatting may be missing. Original: https://arxiv.org/abs/2609.27424