谷歌提出EnvHarness：让静态环境随Agent一起进化
Ranking
Overall
84
Content
90
Popularity
70
Observed public metrics from 1 member.
Merged summary
TL;DR - Google and collaborators propose EnvHarness, a programmable layer that adapts static training environments to an agent’s evolving weaknesses without rebuilding simulators or validators. Its automated EnvRigger system improved held-out task performance by up to 9.0 percentage points while reducing average execution steps by 9.8%.
- EnvHarness modifies environments through three composable components: Stage changes initial states, Contract adjusts interaction rules and observations, and Chain links tasks into longer episodes.
- EnvRigger analyzes successful and failed trajectories, diagnoses policy weaknesses, generates targeted components, and validates them through actual rollouts.
- Across ALFWorld, WebArena, SWE-bench Verified, OfficeQA, and SpreadsheetBench, the approach generally outperformed original environments and domain-specific environment-generation pipelines.
- GRPO experiments showed improved results on three of four reported metrics, suggesting adapted environments can provide better direct reinforcement-learning signals as well as better skill-extraction trajectories.
Sources (1)
谷歌提出EnvHarness：让静态环境随Agent一起进化
Public signals
Hugging Face upvotes 174
TL;DR - Google and collaborators propose EnvHarness, a programmable layer that adapts static training environments to an agent’s evolving weaknesses without rebuilding simulators or validators. Its automated EnvRigger system improved held-out task performance by up to 9.0 percentage points while reducing average execution steps by 9.8%.
- EnvHarness modifies environments through three composable components: Stage changes initial states, Contract adjusts interaction rules and observations, and Chain links tasks into longer episodes.
- EnvRigger analyzes successful and failed trajectories, diagnoses policy weaknesses, generates targeted components, and validates them through actual rollouts.
- Across ALFWorld, WebArena, SWE-bench Verified, OfficeQA, and SpreadsheetBench, the approach generally outperformed original environments and domain-specific environment-generation pipelines.
- GRPO experiments showed improved results on three of four reported metrics, suggesting adapted environments can provide better direct reinforcement-learning signals as well as better skill-extraction trajectories.