Salesforce 研究模型与框架适配问题
Nice paper from Salesforce on co-evolving harnesses and models. Harness engineering is a hot topic ...
Salesforce 发现了模型和框架适配的问题，这个研究挺有意思的，可以看看他们是怎么解决的。
Salesforce 的论文指出，当使用弱模型时，在七项企业任务上的表现会下降 4 到 30 分。这表明模型与框架的适配性至关重要。他们发现，直接模仿专家的完整轨迹会导致弱模型采用专家的策略但无法执行，从而与框架不匹配。解决方案是让元级代理仅重写弱模型失败步骤，以保留其规划风格。
Nice paper from Salesforce on co-evolving harnesses and models. Harness engineering is a hot topic ...
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: academy.dair.ai/papers/co-evol… 💬 6 🔄 1 ❤️ 10 👀 1580 📊 8 ⚡
