Apple

Trends

• Agent training moves off costly live environments

Items

1. Jul 24

   Apple synthesizes API-agent data without environments

   An LLM acting as an on-the-fly world model synthesizes agent trajectories from API specifications alone, yielding fine-tuning gains on AppWorld and OfficeBench without any executable backend.

2. Jun 22

   SelfCompact compacts agent context on demand

   A model-invoked compaction tool fires only when a sub-task resolves or a trajectory converges, matching fixed-interval summarization while improving math accuracy by up to 18.1 points at 30-70% lower per-question cost, with no fine-tuning.

3. May 7

   Apple's TIDE embedding memory

   A plug-in that injects context-free token vectors at every transformer layer through a depth-conditioned router, targeting rare-token undertraining and contextual collapse in small models without modifying the backbone.