Evage automates profitable blockchain trading strategies across chains
EVAGE: Autonomous MEV Generation and Adaptation via Multi-Agent Harness
Cryptography and Security
Summary
Maximal Extractable Value (MEV) lets traders earn profits by choosing the right transactions on blockchains, but this work is usually done by expert teams and requires manual effort. The authors present EVAGE, a system that uses multiple agents to automatically discover, adapt, and transfer MEV strategies across different blockchain networks without human help. EVAGE works by creating and improving MEV trading code offline to ensure fast execution. In tests on major blockchains, EVAGE found new profitable strategies and successfully adapted existing ones, showing its potential to automate a complex and specialized task.
What this means in practice
- •For blockchain developers: Automatically generate and adapt MEV trading bots for multiple blockchain protocols and chains to improve efficiency and reduce manual effort.
- •For crypto trading teams: Create and port profitable MEV strategies across different blockchains and their variants with minimal human intervention and low costs.
Authors
Yan Wen, Zichun Cai, Iliya Mirzaei, Xiaohua Cai, Mohammad Javad Amiri, Haoxian Chen, Chenyuan Wu
Abstract
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.