Microsoft Research: agent skills as trainable parameters (SkillOpt) + token-efficient agent memory (Memora)

Two applied agent-engineering papers (late June 2026): SkillOpt treats agent instruction/skill files as trainable parameters external to a frozen model and reports a +23.5-point absolute improvement for GPT-5.5 on a six-benchmark average; Memora is a memory representation that separates rich content from lightweight abstractions and reports state-of-the-art results while using up to 98% fewer context tokens than full-context baselines.

What it means Concrete, buildable levers: systematically optimizing your skill/instruction files (rather than the model) and compressing agent memory can raise quality and cut token cost — directly applicable if you author skills or run long-horizon agents. Figures are the authors' reported results; validate before quoting.