Metraipolis › archive › dc_47769e019960

GRASP: Generating, Revising, and Assessing for Strategic Planning with Agentic AI — arXiv:2609.30147

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.30147
License (as archived)
CC0-1.0
Archived
2026-10-08T04:19:59.509Z
SHA-256 of the archived text
46023e40841b9422e2cd5d73e02f90002842813e5c10334ffbb6a4963060d0be
Stable URL of this page
https://metraipolis.com/documento/dc_47769e019960

How to cite

GRASP: Generating, Revising, and Assessing for Strategic Planning with Agentic AI — arXiv:2609.30147 — arXiv (en), https://arxiv.org/abs/2609.30147 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_47769e019960 (Metraipolis archive dc_47769e019960, sha256 46023e40841b9422e2cd5d73e02f90002842813e5c10334ffbb6a4963060d0be)
BibTeX
@misc{dc47769e019960,
  title = {GRASP: Generating, Revising, and Assessing for Strategic Planning with Agentic AI — arXiv:2609.30147},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.30147},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_47769e019960; sha256 46023e40841b9422e2cd5d73e02f90002842813e5c10334ffbb6a4963060d0be},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30147. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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$\%$.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.MA).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Machine Learning (cs.LG); Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2609.30147 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T03:50:35.853Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).