Dark | Light
[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]

![omarsar0 Avatar](https://lunarcrush.com/gi/w:24/cr:twitter::3448284313.png) elvis [@omarsar0](/creator/twitter/omarsar0) on x 255.9K followers
Created: 2025-07-22 20:09:21 UTC

An ablation study shows the importance of explicitly including tool names and I/O descriptions in Routine steps.

Removing tool names dropped Qwen3-14B’s accuracy from XXXX% to 71.9%. Adding I/O fields provided minor gains, especially for less capable models.

![](https://pbs.twimg.com/media/GwfNEDWbEAAF45v.png)

XXX engagements

![Engagements Line Chart](https://lunarcrush.com/gi/w:600/p:tweet::1947750835334877352/c:line.svg)

**Related Topics**
[elvis](/topic/elvis)

[Post Link](https://x.com/omarsar0/status/1947750835334877352)

[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]

omarsar0 Avatar elvis @omarsar0 on x 255.9K followers Created: 2025-07-22 20:09:21 UTC

An ablation study shows the importance of explicitly including tool names and I/O descriptions in Routine steps.

Removing tool names dropped Qwen3-14B’s accuracy from XXXX% to 71.9%. Adding I/O fields provided minor gains, especially for less capable models.

XXX engagements

Engagements Line Chart

Related Topics elvis

Post Link

post/tweet::1947750835334877352
/post/tweet::1947750835334877352