Abstract
Large Language Models (LLMs) typically exhibit a performance profile where reliability degrades as task complexity increases. We address the challenge of generating high-quality natural language executable plans for complex tasks by introducing $\textbf{GRASP}$, a strategy-aware, multi-stage planning framework. GRASP decouples the planning pipeline across specialized, context-isolated modules: it pre-compiles global macro-guidelines (GenPlan), explores alternative localized strategies within isolated context windows (RevPlan), and independently evaluates trajectories using a multi-criteria discriminator (VerPlan). Empirical evaluations show that GRASP consistently establishes a new state-of-the-art frontier across diverse datasets, yielding substantial accuracy gains over direct LLM planners on Natural Plan Calendar Scheduling ($\sim$12.4$\%$$\uparrow$), ZebraLogic ($\sim$30.8$\%$$\uparrow$), and SciBench Math. Crucially, under multi-task scaling-where standard planners suffer immediate performance collapse-GRASP completely flattens the multi-task degradation penalty. In interleaved dual-task environments, GRASP achieves an absolute accuracy gain of up to 16.7$\%$ over direct LLM planners. Furthermore, by isolating context and enforcing strict macro-regularization, GRASP outperforms frontier reasoning models (such as GPT-5-mini) by a margin of 14.5$\%$.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Srivastava, A., A., M., Khojastepour, Chakradhar, S., & Ulukus, S. (2026). GRASP: Generating, Revising, and Assessing for Strategic Planning with Agentic AI. https://omanscience.com/en/articles/grasp-generating-revising-and-assessing-for-strategic-planning-with-agentic-ai
MLA 9
Srivastava, Arunabh, et al. "GRASP: Generating, Revising, and Assessing for Strategic Planning with Agentic AI." https://omanscience.com/en/articles/grasp-generating-revising-and-assessing-for-strategic-planning-with-agentic-ai.
Chicago (author–date)
Srivastava, Arunabh, Mohammad A., Khojastepour, Srimat Chakradhar, and Sennur Ulukus. 2026. "GRASP: Generating, Revising, and Assessing for Strategic Planning with Agentic AI." https://omanscience.com/en/articles/grasp-generating-revising-and-assessing-for-strategic-planning-with-agentic-ai.
Harvard
Srivastava, A., A., M., Khojastepour, Chakradhar, S. and Ulukus, S. (2026) 'GRASP: Generating, Revising, and Assessing for Strategic Planning with Agentic AI', Available at: https://omanscience.com/en/articles/grasp-generating-revising-and-assessing-for-strategic-planning-with-agentic-ai.
Vancouver
Srivastava A, A. M, Khojastepour, Chakradhar S, Ulukus S. GRASP: Generating, Revising, and Assessing for Strategic Planning with Agentic AI. https://omanscience.com/en/articles/grasp-generating-revising-and-assessing-for-strategic-planning-with-agentic-ai
IEEE
A. Srivastava, M. A., Khojastepour, S. Chakradhar, and S. Ulukus, "GRASP: Generating, Revising, and Assessing for Strategic Planning with Agentic AI," https://omanscience.com/en/articles/grasp-generating-revising-and-assessing-for-strategic-planning-with-agentic-ai.