# EnvHarness：让智能体训练环境动态适应

- 来源：Rohan Paul (@rohanpaul_ai)
- 发布时间：2026-08-22 10:11
- AIHOT 分数：37
- AIHOT 链接：https://aihot.virxact.com/items/cmt3r16fw0zikro6ti260ruwe
- 原文链接：https://x.com/rohanpaul_ai/status/2090985245348975082

## AI 摘要

Google 新论文提出 EnvHarness，通过重塑现有环境来针对智能体弱点进行训练，同时保持原任务和验证器不变。EnvRigger 自动发现弱点并生成包装器，仅在验证有效后保留。在 SWE-bench Verified 上，同等 300 环境预算下，智能体解决率达 54.79%，优于原始环境的 52.13% 和生成环境的 50.37%。

## 正文

Another great Google paper.

Agent training has a ceiling: the agent improves, but the same environment stays frozen.

EnvHarness makes the environment adapt too, without rebuilding the benchmark or its verifier.

EnvHarness does this by reshaping an existing environment around whatever the agent is currently bad at, while keeping the original task and verifier intact.

If a coding agent skips tests, for example, the environment can reject submission until tests run; if it relies on a shortcut, that shortcut can be blocked.

EnvRigger finds these weaknesses from rollouts, writes the wrapper, then keeps it only if fresh runs show the new setup is both useful and solvable.

On SWE-bench Verified, with the same 300-environment budget, agents resolved 54.79% of issues, versus 52.13% with original environments and 50.37% with generated ones.

– arxiv. org/abs/2608.19880

Title: "EnvHarness: Awakening Static Worlds for Agent Learning"