Microsoft's ActiveSaddler Uses Automated Curriculum Learning to Boost Agent Harnesses by 7.5 Points
microsoft · hf · 2026-10-02
Microsoft introduces ActiveSaddler, framing training-scenario selection as the missing dimension of automated agent harness optimization. Existing methods update prompts, tool interfaces, and control logic from execution feedback while fixing the scenario curriculum; ActiveSaddler instead models the evolving curriculum as a non-stationary bandit with dynamically instantiated failure-pattern arms, balancing revisiting known weaknesses with exploring unseen scenarios. On GAIA2 and Terminal-Bench 2.0 it improves test Pass@1 by 4.4 and 7.5 percentage points over a fixed-order curriculum, with ablations confirming the gains come from dynamic target construction and utility estimation.
More from coding & agent
- AI in finance shows a power law: top 1% users generate 35x more files with agents — peterjliu · 2026-11-19
- Linux LTS patch flood: 3318 patches for 6.6 alone, 'no way humans are reviewing this' — pkqzy888 · 2026-11-19
- Caliper Harness: open-source coding harness disciplines small local models with plans, checks, reviews — Saraozte01 · 2026-11-19
- AI systems lack executive function, not scale: four manager-layer strategies to fix it — Designer-Material633 · 2026-11-19
- Google employee replaces doomscrolling with 3 fully automated personal AI newsletters — DynamicWebPaige · 2026-11-19
- Designer spins up an agent to build state-airline brand gallery mid-flight delay — beh_zod · 2026-11-19