AutoResearch — Autonomous DEX Strategy Discovery

Problem Statement

Most trading bots are static: someone writes a strategy, deploys it, and prays. When markets shift, the strategy breaks and a human has to manually intervene. AutoResearch eliminates the human bottleneck by running a continuous research loop — proposing hypotheses via LLM, backtesting against real Base DEX data, keeping only improvements, and learning from every failure through persistent LCM memory. The result: an agent that improves itself. ## Problem Statement Most trading bots are static: someone writes a strategy, deploys it, and prays. When markets shift, the strategy breaks and a human has to manually intervene. There is no systematic way for an autonomous agent to discover, test, and improve its own trading strategies without human involvement. AutoResearch eliminates the human bottleneck by running a continuous research loop — proposing hypotheses via LLM, backtesting against real Base DEX data, keeping only improvements, and learning from every failure through persistent LCM memory. The result: an agent that improves itself. ## Problem Statement Most trading bots are static: someone writes a strategy, deploys it, and prays. When markets shift, the strategy breaks and a human has to manually intervene. There is no systematic way for an autonomous agent to discover, test, and improve its own trading strategies without human involvement. AutoResearch eliminates the human bottleneck by running a continuous research loop — proposing hypotheses via LLM, backtesting against real Base DEX data, keeping only improvements, and learning from every failure through persistent LCM memory. The result: an agent that improves itself.