Skill adaptation improves weak models in harness self-evolution
Across 103 task-skill pairs, skills that raise GPT-5.6-luna by 31.1 points lower Gemma-4-E4B by 8.8.
48
AI model
Gemma-4-e4b
- Mentions · 7d0
- Mentions · 30d1
- All mentions2
- First seenSep 20, 2026
- Last mentioned21d ago
Timeline
2 articles · newest firstEDGEGEN: Improving Tool-Calling Agents Beyond Happy Paths with Synthetic Edge Case Generation
EdgeGen synthesizes database-grounded edge-case tasks that improve tool-calling agents without human annotation.
48
Appears with
- Kimi-K2.5ai model · 1
- GPT-5.6-lunaai model · 1
- EdgeGenproduct · 1
- tau2-benchproduct · 1
- Kimi-K3ai model · 1
- Google DeepMindorganization · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.