Agents
Great paper from Microsoft and colleagues on optimizing agent harnesses. Current harness optimizers change how the harness is updated but ke…
Great paper from Microsoft and colleagues on optimizing agent harnesses. Current harness optimizers change how the harness is updated but keep the training scenarios fixed, so feedback keeps coming fr
Great paper from Microsoft and colleagues on optimizing agent harnesses. Current harness optimizers change how the harness is updated but keep the training scenarios fixed, so feedback keeps coming from tasks that stop being informative as the harness improves. This work adapts the scenarios as well. ActiveSaddler groups recurring failures into failure patterns and treats each pattern as an arm in a non-stationary bandit. It tracks how much the harness is still learning from each pattern and splits the budget between revisiting known weaknesses and finding new ones. With the same optimizer, test Pass@1 improves by 4.4 points on GAIA2 and 7.5 points on Terminal-Bench 2.0 compared with a fixed scenario order. Paper: https://academy.dair.ai/papers/activesaddler-automated-curriculum-learning-for-agent-harness-optimization-2610.00906
Related
- Great paper on self-evolving agent harnesses. Self-evolving agent harnesses have two practical problems: 1. Search is slow, because every ca…
- Great paper from Microsoft Research and colleagues. If you auto-generate MCP tools from agent trajectories, this one is worth your time. Aut…
- Impressive new paper from Microsoft and colleagues. Harness design is still hand-tuned almost everywhere. This work present an automated loo…
Source: DAIR.AI (X) | 2026-10-04