PEEU enables a 7B MLLM to reach 30.6% accuracy on GUI task planning by autonomous exploration and hindsight experience synthesis, outperforming a 32B model through stronger high-level OOD generalization.
Largelanguagemodelsforplanning: Acomprehensiveandsystematicsurvey
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
abstract
Planning represents a fundamental capability of intelligent agents, requiring comprehensive environmental understanding, rigorous logical reasoning, and effective sequential decision-making. While Large Language Models (LLMs) have demonstrated remarkable performance on certain planning tasks, their broader application in this domain warrants systematic investigation. This paper presents a comprehensive review of LLM-based planning. Specifically, this survey is structured as follows: First, we establish the theoretical foundations by introducing essential definitions and categories about automated planning. Next, we provide a detailed taxonomy and analysis of contemporary LLM-based planning methodologies, categorizing them into three principal approaches: 1) External Module Augmented Methods that combine LLMs with additional components for planning, 2) Finetuning-based Methods that involve using trajectory data and feedback signals to adjust LLMs in order to improve their planning abilities, and 3) Searching-based Methods that break down complex tasks into simpler components, navigate the planning space, or enhance decoding strategies to find the best solutions. Subsequently, we systematically summarize existing evaluation frameworks, including benchmark datasets, evaluation metrics and performance comparisons between representative planning methods. Finally, we discuss the underlying mechanisms enabling LLM-based planning and outline promising research directions for this rapidly evolving field. We hope this survey will serve as a valuable resource to inspire innovation and drive progress in this field.
citation-role summary
background 2
baseline 1
citation-polarity summary
representative citing papers
ClassicLogic is an open-source benchmark using four logic puzzles with a hierarchical strategy knowledge base to evaluate three forms of compositional generalization in AI agents.
This survey categorizes agentic environments for LLMs by eight attributes and domains, introduces symbolic and neural synthesis paradigms with evaluation, and outlines four agent evolution pathways plus three environment evolution paradigms.
AdaPlan-H enables LLM agents to generate self-adaptive hierarchical plans that adjust detail level to task difficulty, improving success rates in multi-step tasks.
DocArena automates creation of multimodal document QA training data via MLLM-based structuring and cross-page reasoning pairs, yielding agents with top retrieval and QA performance in unified tests.
A survey proposing a three-level capability taxonomy (L1 Predictor, L2 Simulator, L3 Evolver) for world models across physical, digital, social, and scientific domains.
The survey organizes Context Engineering into retrieval, processing, management, and integrated systems like RAG and multi-agent setups while identifying an asymmetry where LLMs handle complex inputs well but struggle with equally sophisticated long outputs.
citing papers explorer
-
Empowering GUI Agents via Autonomous Experience Exploration and Hindsight Experience Utilization for Task Planning
PEEU enables a 7B MLLM to reach 30.6% accuracy on GUI task planning by autonomous exploration and hindsight experience synthesis, outperforming a 32B model through stronger high-level OOD generalization.
-
ClassicLogic: A Knowledge-Driven Benchmark of Classic Puzzle Games for Evaluating Compositional Generalization
ClassicLogic is an open-source benchmark using four logic puzzles with a hierarchical strategy knowledge base to evaluate three forms of compositional generalization in AI agents.
-
Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application
This survey categorizes agentic environments for LLMs by eight attributes and domains, introduces symbolic and neural synthesis paradigms with evaluation, and outlines four agent evolution pathways plus three environment evolution paradigms.
-
From Coarse to Fine: Self-Adaptive Hierarchical Planning for LLM Agents
AdaPlan-H enables LLM agents to generate self-adaptive hierarchical plans that adjust detail level to task difficulty, improving success rates in multi-step tasks.
-
DocArena: Turning Raw Documents into Controllable Training Environments for Document Search Agents
DocArena automates creation of multimodal document QA training data via MLLM-based structuring and cross-page reasoning pairs, yielding agents with top retrieval and QA performance in unified tests.
-
Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond
A survey proposing a three-level capability taxonomy (L1 Predictor, L2 Simulator, L3 Evolver) for world models across physical, digital, social, and scientific domains.
-
A Survey of Context Engineering for Large Language Models
The survey organizes Context Engineering into retrieval, processing, management, and integrated systems like RAG and multi-agent setups while identifying an asymmetry where LLMs handle complex inputs well but struggle with equally sophisticated long outputs.