# Salesforce 论文提出在策略修正，解决 harness 与模型协同进化中的模仿失效问题

- 来源：elvis (@omarsar0)
- 发布时间：2026-09-10 16:00
- AIHOT 分数：50
- AIHOT 链接：https://aihot.news/items/cmtv8z5v2055xrok9prpqbilk
- 原文链接：https://x.com/omarsar0/status/2097958286146605446

## AI 摘要

Salesforce AI 发布论文《Co-Evolving Harnesses and Models: On-Policy Correction Helps Weaker Models Catch Up Where Imitation Fails》。

## 正文

Nice paper from Salesforce on co-evolving harnesses and models.

Harness engineering is a hot topic right now. So this is a great read.

(bookmark it)

Salesforce evolved a harness with a weak model across seven enterprise agent tasks, then trained that model on a stronger expert's full trajectories under the same harness.

Performance dropped on all seven tasks, by 4 to 30 points across Qwen3-Coder and Gemma 4.

The same fine-tuning helps under the unevolved harness. So the harness is what changes the outcome.

Their analysis points at model-harness fit.

Imitation transfers knowledge and increases scaffold usage, but the weaker model adopts the expert's planning strategy without the competence to execute it, and it no longer matches a harness that was evolved around its own native planning style.

The fix is to stop copying whole trajectories.

A meta-level agent finds the failing turn in the weaker model's own rollout and asks the expert to rewrite only that turn. That keeps the model's planning style intact and combines the gains from harness evolution and weight updates.

Paper: https://academy.dair.ai/papers/co-evolving-harnesses-and-models-on-policy-correction-helps-weaker-models-catch-2609.09134