Dolores Research Deploys WAGMI Bench for AI Trading Agent Evaluations

Dolores Research has launched WAGMI Bench, an open-source benchmark for evaluating AI trading agents on Virtuals Protocol. The framework assesses agents across 13 historical periods in the BTC perpetuals market, covering events from the COVID crash to ETH approvals.

Unlike traditional profit-and-loss metrics, WAGMI Bench focuses on survival and engagement metrics. This approach aims to provide a more comprehensive understanding of an agent's performance.

The project draws inspiration from SWE-bench, which established a standard for measuring AI coding agents' capabilities. Dolores Research has released WAGMI Bench under the Apache-2.0 license, allowing developers to modify and extend it as needed.

Alongside WAGMI Bench, Dolores Research launched a community token called $DOLORES through the Virtuals Protocol on Robinhood Chain. The token's allocation includes 2% of its total supply for veVIRTUAL stakers, connecting the project to the broader Virtuals ecosystem.