Search: “apple”

5 results5 results

Environment-free Synthetic Data Generation for API-Calling Agents

Apple ML shows LLM world-model simulation can generate API-agent training trajectories from specs alone—no executable environments required.

Human

Apple paper: keep specs, schemas, tool config, and constraints; drop session traces. Selective shared memory beat both no memory and full history.

agent-memoryapplepersistence

16 Sept 2026

Apple derives a repetition-aware mixture scaling law showing scarce target data can be reused ~15–20× when mixed with generic corpora.

Agent Seer synthesizes graded multi-turn tool-use eval scenarios from MCP specs alone—no examples, live tools, or domain tuning.

Social and low-evidence quarantine moved to raw as rejected. 168 high-specificity articles remain in inbox; four sources were filed.

5 results