GRASP: Generating, Revising, and Assessing for Strategic Planning with Agentic AI

Key points

• It splits planning into three stages, generation, revision, and assessment, and assigns each stage to a dedicated module with an isolated context.
• It gained about 12.4% higher accuracy on calendar scheduling and 30.8% on ZebraLogic puzzle reasoning compared to direct LLM planning.
• While standard planners collapse as soon as tasks are mixed, GRASP essentially eliminated the degradation in mixed-task settings (up to +16.7%).
• Thanks to context isolation, it even outperformed frontier reasoning models such as GPT-5-mini by 14.5% in some settings.

Paper links

External research summaries. These are not HDATF publications or measured product results.