智能体
arxiv.org ·
GRASP：基于智能体 AI 的生成、修订与评估战略规划框架
该论文提出 GRASP，一种策略感知的多阶段规划框架，将规划流程解耦为三个上下文隔离的模块：GenPlan 预编译全局宏观准则，RevPlan 在隔离上下文窗口中探索局部替代策略，VerPlan 用多准则判别器独立评估轨迹。作者报告在 Natural Plan Calendar Scheduling 上较直接 LLM 规划器提升约 12.4%，ZebraLogic 提升约 30.8%，SciBench Math 亦有提升；在多任务扩展场景下消除了标准规划器的性能崩溃，交错双任务环境绝对准确率最高提升 16.7%，并称比 GPT-5-mini 等前沿推理模型高 14.5%。上述结果均为作者自报，尚待独立验证。
AI推荐理由 arXiv 新提交论文（2026-09-24），提出 GRASP 多阶段智能体规划框架，将规划流程解耦为 GenPlan（生成宏观准则）、RevPlan（隔离上下文内探索局部策略）和 VerPlan（多准则判别器独立评估轨迹）。摘要给出具体量化结果：Natural Plan Calendar Scheduling 提升约 12.4%、ZebraLogic 约 30.8%、SciBench Math 亦有提升；多任务扩展下消除性能退化惩罚，交错双任务环境绝对准确率提升最高 16.7%，并称比 GPT-5-mini 等前沿推理模型高 14.5%。信息密度高、方法描述具体，但结果均为作者自报，尚无第三方复现或代码验证，且 arXiv 编号与日期较新，需谨慎看待。
78
正文
Computer Science > Artificial Intelligence
arXiv:2609.30147 (cs)
[Submitted on 24 Sep 2026]
Title:GRASP: Generating, Revising, and Assessing for Strategic Planning with Agentic AI
Authors:Arunabh Srivastava, Mohammad A. (Amir)Khojastepour, Srimat Chakradhar, Sennur Ulukus
View a PDF of the paper titled GRASP: Generating, Revising, and Assessing for Strategic Planning with Agentic AI, by Arunabh Srivastava and 2 other authors
View PDF
HTML (experimental)
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$\%$.
Comments:
Subjects:
Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG); Multiagent Systems (cs.MA)
Cite as:
arXiv:2609.30147 [cs.AI]
(or
arXiv:2609.30147v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2609.30147
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Arunabh Srivastava [view email]
[v1]
Thu, 24 Sep 2026 17:11:35 UTC (195 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled GRASP: Generating, Revising, and Assessing for Strategic Planning with Agentic AI, by Arunabh Srivastava and 2 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.AI
new
|
recent
| 2026-09
Change to browse by:
cs
cs.CL
cs.LG
cs.MA
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)