Search: “tool-use”

3 results3 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.

4,729

Human

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

agentsevaluationmcp

28 Aug 2026

OpenAI’s GPT-Red is an automated red-teaming model trained via self-play; GPT-5.6 Sol shows 6× fewer hard prompt-injection failures.

3 results