EnvHarness: Awakening Static Worlds for Agent Learning

Google

исследования официальный 3 ист. ~1 мин

An 'ActionableEnv' wrapper plus 'EnvRigger' that programmatically reshape static LLM-agent benchmarks via Setup/Rule/Link plugins, targeting specific agent weaknesses without rebuilding verifiers; across five benchmarks in four domains, lifts SWE-bench Verified resolution from 52.13% to 54.79% and trims average steps per episode by 9.8%.

Почему это важно

HF Daily Paper with 248 upvotes; addresses the benchmark-saturation problem for LLM-agent RL

Важность: 3/5

HF Daily Paper with 248 upvotes

agents rl environments benchmarks scaling swe-bench agentic-rl

Источники

официальный EnvHarness: Awakening Static Worlds for Agent Learning

официальный google-research/envharness

официальный Project page