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
- LAHacks build Residue uses acoustic analysis and AI agents to personalize your study environment — jonmarkgo · 2026-10-02
- awesome-jev indexes 700 production tools around TypeSafe AI's decision model Jev — Remarkable-Gur719 · 2026-10-02
- $10k of AI inference ports TS to C++ in days, a job for expert teams over years — kristoph · 2026-10-02
- Basis Theory launches revocable credentials letting AI agents act without touching your secrets — km · 2026-10-02
- smolvm v1.22 ships near-instant VM resume for undoing agent actions, 6.5k stars — LoganGrasby · 2026-10-02
- Jacob Sansbury essay: assume a few years of normalcy left, SaaS and productivity tools are dead ideas — TAbrodi · 2026-10-02