Cover Image

Learning and Reusing Policy Decompositions for Hierarchical Generalized Planning with LLM Agents

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sohrabi, Shirin, Ananthakrishnan, Haritha, Kokel, Harsha, Srinivas, Kavitha, Katz, Michael
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Planning in the LLM Era: Building for Reliability and Efficiency
by: Katz, Michael, et al.
Published: (2026)

ACPBench: Reasoning about Action, Change, and Planning
by: Kokel, Harsha, et al.
Published: (2024)

Thought of Search: Planning with Language Models Through The Lens of Efficiency
by: Katz, Michael, et al.
Published: (2024)

ACPBench Hard: Unrestrained Reasoning about Action, Change, and Planning
by: Kokel, Harsha, et al.
Published: (2025)

QueryGym: Step-by-Step Interaction with Relational Databases
by: Ananthakrishnan, Haritha, et al.
Published: (2025)

Large Language Models as Planning Domain Generators
by: Oswald, James, et al.
Published: (2024)

Automating Thought of Search: A Journey Towards Soundness and Completeness
by: Cao, Daniel, et al.
Published: (2024)

Model Space Reasoning as Search in Feedback Space for Planning Domain Generation
by: Oswald, James, et al.
Published: (2026)

Make Planning Research Rigorous Again!
by: Katz, Michael, et al.
Published: (2025)

Can Cross Encoders Produce Useful Sentence Embeddings?
by: Ananthakrishnan, Haritha, et al.
Published: (2025)

Seemingly Simple Planning Problems are Computationally Challenging: The Countdown Game
by: Katz, Michael, et al.
Published: (2025)

Unifying and Certifying Top-Quality Planning
by: Katz, Michael, et al.
Published: (2024)

Less is More: Learning Graph Tasks with Just LLMs
by: Shirai, Sola, et al.
Published: (2025)

Some Orders Are Important: Partially Preserving Orders in Top-Quality Planning
by: Katz, Michael, et al.
Published: (2024)

TOPJoin: A Context-Aware Multi-Criteria Approach for Joinable Column Search
by: Kokel, Harsha, et al.
Published: (2025)

Evaluating Joinable Column Discovery Approaches for Context-Aware Search
by: Kokel, Harsha, et al.
Published: (2025)

Combining Planning and Reinforcement Learning for Solving Relational Multiagent Domains
by: Prabhakar, Nikhilesh, et al.
Published: (2025)

TabSketchFM: Sketch-based Tabular Representation Learning for Data Discovery over Data Lakes
by: Khatiwada, Aamod, et al.
Published: (2024)

On Policy Reuse: An Expressive Language for Representing and Executing General Policies that Call Other Policies
by: Bonet, Blai, et al.
Published: (2024)

Hierarchical Task Network Planning with LLM-Generated Heuristics
by: Meneguzzi, Felipe, et al.
Published: (2026)

From Coarse to Fine: Self-Adaptive Hierarchical Planning for LLM Agents
by: Tan, Haoran, et al.
Published: (2026)

LLM-Powered Decentralized Generative Agents with Adaptive Hierarchical Knowledge Graph for Cooperative Planning
by: Yang, Hanqing, et al.
Published: (2025)

Learning Abstractions for Hierarchical Planning in Program-Synthesis Agents
by: Ahmed, Zergham, et al.
Published: (2026)

When Continual Learning Moves to Memory: A Study of Experience Reuse in LLM Agents
by: Hu, Qisheng, et al.
Published: (2026)

HiPlan: Hierarchical Planning for LLM-Based Agents with Adaptive Global-Local Guidance
by: Li, Ziyue, et al.
Published: (2025)

DHP: Discrete Hierarchical Planning for Hierarchical Reinforcement Learning Agents
by: Sharma, Shashank, et al.
Published: (2025)

SkillLens: Adaptive Multi-Granularity Skill Reuse for Cost-Efficient LLM Agents
by: Miao, Yongliang, et al.
Published: (2026)

Deconstructing Spatial Complexity: Hierarchical Decomposition for LLM Spatial Reasoning
by: Wang, Yi, et al.
Published: (2026)

Generalized Policy Improvement Algorithms with Theoretically Supported Sample Reuse
by: Queeney, James, et al.
Published: (2022)

MiGrATe: Mixed-Policy GRPO for Adaptation at Test-Time
by: Phan, Peter, et al.
Published: (2025)

LAMARL: LLM-Aided Multi-Agent Reinforcement Learning for Cooperative Policy Generation
by: Zhu, Guobin, et al.
Published: (2025)

Efficient Lookahead Encoding and Abstracted Width for Learning General Policies in Classical Planning
by: Aichmüller, Michael, et al.
Published: (2026)

ReAcTree: Hierarchical LLM Agent Trees with Control Flow for Long-Horizon Task Planning
by: Choi, Jae-Woo, et al.
Published: (2025)

Decomposition-based Hierarchical Task Allocation and Planning for Multi-Robots under Hierarchical Temporal Logic Specifications
by: Luo, Xusheng, et al.
Published: (2023)

Prism: Policy Reuse via Interpretable Strategy Mapping in Reinforcement Learning
by: Pravetz, Thomas
Published: (2026)

Why Do LLM-based Web Agents Fail? A Hierarchical Planning Perspective
by: Aghzal, Mohamed, et al.
Published: (2026)

Proposing Hierarchical Goal-Conditioned Policy Planning in Multi-Goal Reinforcement Learning
by: Rens, Gavin B.
Published: (2025)

Power and Limitations of Aggregation in Compound AI Systems
by: Ananthakrishnan, Nivasini, et al.
Published: (2026)

LLM-mediated Dynamic Plan Generation with a Multi-Agent Approach
by: Abe, Reo, et al.
Published: (2025)

Can AI autonomously build, operate, and use the entire data stack?
by: Agarwal, Arvind, et al.
Published: (2025)