# EVAGE: Autonomous MEV Generation and Adaptation via Multi-Agent Harness

arXiv: https://arxiv.org/abs/2609.27424 · HTML: https://mlsanity.com/paper/2609.27424/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 50 references that are in the map.
- First posted on arXiv 23 Sep 2026.

## Placed in

- LLM agents and tool use

## Builds on (most cited first, 20 of 20)

- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [SoK: Decentralized Exchanges (DEX) with Automated Market Maker (AMM) Protocols](https://mlsanity.com/paper/2103.12732/) (2021)
- [Quantifying Blockchain Extractable Value: How dark is the forest?](https://mlsanity.com/paper/2101.05511/) (2021)
- [An analysis of Uniswap markets](https://mlsanity.com/paper/1911.03380/) (2019)
- [High-Frequency Trading on Decentralized On-Chain Exchanges](https://mlsanity.com/paper/2009.14021/) (2020)
- [Frontrunner Jones and the Raiders of the Dark Forest: An Empirical Study of Frontrunning on the Ethereum Blockchain](https://mlsanity.com/paper/2102.03347/) (2021)
- [On the Just-In-Time Discovery of Profit-Generating Transactions in DeFi Protocols](https://mlsanity.com/paper/2103.02228/) (2021)
- [A Flash(bot) in the Pan: Measuring Maximal Extractable Value in Private Pools](https://mlsanity.com/paper/2206.04185/) (2022)
- [Cyclic Arbitrage in Decentralized Exchanges](https://mlsanity.com/paper/2105.02784/) (2021)
- [Extracting Godl [sic] from the Salt Mines: Ethereum Miners Extracting Value](https://mlsanity.com/paper/2203.15930/) (2022)
- [Rolling in the Shadows: Analyzing the Extraction of MEV Across Layer-2 Rollups](https://mlsanity.com/paper/2405.00138/) (2024)
- [Maximal Extractable Value in Decentralized Finance: Taxonomy, Detection, and Mitigation](https://mlsanity.com/paper/2411.03327/) (2024)
- [Following Devils' Footprint: Towards Real-time Detection of Price Manipulation Attacks](https://mlsanity.com/paper/2502.03718/) (2025)
- [Demystifying DeFi MEV Activities in Flashbots Bundle](https://mlsanity.com/paper/2312.01091/) (2023)
- [TxRay: Agentic Postmortem of Live Blockchain Attacks](https://mlsanity.com/paper/2602.01317/) (2026)
- [When Priority Fails: Revert-Based MEV on Fast-Finality Rollups](https://mlsanity.com/paper/2506.01462/) (2025)
- [The Express Lane to Spam and Centralization: An Empirical Analysis of Arbitrum's Timeboost](https://mlsanity.com/paper/2509.22143/) (2025)
- [Where Does MEV Really Come From? Revisiting CEXDEX Arbitrage on Ethereum](https://mlsanity.com/paper/2604.15973/) (2026)
- [Censorship-Resistant Sealed-Bid Auctions on Blockchains](https://mlsanity.com/paper/2606.14939/) (2026)

## Abstract (arXiv)

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× to 15.97×. 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.