Google open-sources EnvHarness to adapt training environments for self-evolving agents

KEY POINTS

1. Google researchers open-sourced EnvHarness, a framework that wraps static environments via the standard reset()/step() interface and applies composable setup, rule, and link mutations so environments adapt to an agent's weaknesses without changing the underlying environment or evaluators.
2. The release also includes EnvRigger, an automated loop that analyzes agent rollouts to generate and validate targeted environment edits; Google reports consistent performance gains (≈2.9–3.7 percentage points) across benchmarks such as WebArena, SWE-bench Verified, and ALFWorld on models including Gemini, Qwen, and Claude Sonnet.
3. EnvHarness offers a domain-agnostic, benchmark-preserving way to co-evolve environments with agents, which can improve learning efficiency and help agents continue to make progress when static benchmarks plateau.