# Meta 新研究：EvoHarness-RL 让智能体自主学习工具编排策略

- 来源：elvis (@omarsar0)
- 发布时间：2026-08-10 01:45
- AIHOT 分数：37
- AIHOT 链接：https://aihot.virxact.com/items/cmsm4gcaf08mnroy9j2sel8n3
- 原文链接：https://x.com/omarsar0/status/2086509069762981896

## AI 摘要

Meta 新研究提出 EvoHarness-RL，让智能体离线学习工具编排（harness）策略，并在运行时在线更新外部状态，替代手工编写。Qwen3-8B 在 ALFWorld 上达到 96.9% 准确率。训练中出现的“工具编排退火”与“工具编排进化”两种动态表明，长程任务智能体从可训练的协调策略中获益，胜过更大的工具集或记忆。

## 正文

New research from Meta.

Agent harnesses are still mostly authored by hand.

This makes it hard to tune robust agent harnesses for long-horizon tasks.

In this new work, agents learn harness policies offline and deploy them to construct and update external harness state online during runtime task execution.

EvoHarness-RL learns that policy instead. Belief, Progress, and Experience are exposed as harness state the policy can act on.

Supervised harness fine-tuning teaches the action space, then cost-aware GRPO explores when to read, update, and consolidate during a long run. Qwen3-8B reaches 96.9% on ALFWorld.

Two dynamics come out of the training.

Harness annealing means recurring harness-use patterns get absorbed into the model policy, and the agent shifts from frequent calls toward selective access.

Harness evolution means progress updates and experience consolidation compress the workspace into a compact task-adaptive state.

This shows that long-horizon agents get more from a trainable coordination policy than from bigger tools or larger memories.

Paper: https://arxiv.org/abs/2608.05446

Track more trending AI papers in our academy: https://academy.dair.ai/