[Evolvent AI Open Sources RSIGym, Claude Opus 5 Boosts Qwen Model SWE-bench Performance Nearly Threefold] According to Deep Tide TechFlow, on October 8, Evolvent AI released the open-source research environment RSIGym, enabling AI agents to retrain models and rewrite harnesses within a unified budget framework. As disclosed by X user Rohan Paul, within this environment, Claude Opus 5, acting as an automated AI researcher, boosted the performance of a Qwen model on SWE-bench Verified nearly threefold. RSIGym is designed to provide a research environment under unified budget constraints, allowing agents to retrain models and rewrite evaluation harnesses, thereby enabling comparisons of different agents' research capabilities under the same conditions. The environment is now open-sourced.