Graph-enhanced Large Language Models in Asynchronous Plan Reasoning

2024-02-05 · Fangru Lin, Emanuele La Malfa, Valentin Hofmann, Elle Michelle Yang, Anthony Cohn, Janet B. Pierrehumbert

Planning is a fundamental property of human intelligence. Reasoning about asynchronous plans is challenging since it requires sequential and parallel planning to optimize time costs. Can large language models (LLMs) succeed at this task? Here, we present the first large-scale study investigating this question. We find that a representative set of closed and open-source LLMs, including GPT-4 and LLaMA-2, behave poorly when not supplied with illustrations about the task-solving process in our benchmark AsyncHow. We propose a novel technique called Plan Like a Graph (PLaG) that combines graphs with natural language prompts and achieves state-of-the-art results. We show that although PLaG can boost model performance, LLMs still suffer from drastic degradation when task complexity increases, highlighting the limits of utilizing LLMs for simulating digital devices. We see our study as an exciting step towards using LLMs as efficient autonomous agents. Our code and data are available at https://github.com/fangru-lin/graph-llm-asynchow-plan.

📄 PDF Abstract BibTeX arXiv:2402.02805

Code (1)

fangru-lin/graph-llm-asynchow-plan 공식 구현

Methods 이 논문이 사용한 방법론

Attention 설명 없음

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Multi-Head Attention 설명 없음

Adam 설명 없음

Residual Connection 설명 없음

Asynchronous Large Language Model Enhanced Planner for Autonomous Driving

2024-06-20 · Yuan Chen, Zi-han Ding, Ziqin Wang, Yan Wang 외

Despite real-time planners exhibiting remarkable performance in autonomous driving, the growing exploration of Large Language Models (LLMs) has opened avenues for enhancing the interpretability and controllability of mot…

Autonomous Driving Language Modeling Language Modelling Large Language Model+1

Embodied Task Planning via Graph-Informed Action Generation with Large Language Models

2026-01-29 · Xiang Li, Ning Yan, Masood Mortazavi arxiv

While Large Language Models (LLMs) have demonstrated strong zero-shot reasoning capabilities, their deployment as embodied agents still faces fundamental challenges in long-horizon planning. Unlike open-ended text genera…

Graph Neural Network Text Generation

Robotouille: An Asynchronous Planning Benchmark for LLM Agents

2025-02-06 · Gonzalo Gonzalez-Pumariega, Leong Su Yean, Neha Sunkara, Sanjiban Choudhury

Effective asynchronous planning, or the ability to efficiently reason and plan over states and actions that must happen in parallel or sequentially, is essential for agents that must account for time delays, reason over …

Language Modeling Language Modelling Large Language Model Task Planning

Robust Asynchronous Planning via Auto-Formalization

2026-05-31 · Jiayi Zhang, Jianing Yin, Ben Zhou, Li Zhang arxiv

LLMs can plan by either generating action sequences directly as a Planner or translating tasks into domain specific language for an external solver as a Formalizer. While most real-world tasks are asynchronous with non-u…

SFCo-Nav: Efficient Zero-Shot Visual Language Navigation via Collaboration of Slow LLM and Fast Attributed Graph Alignment

2026-03-02 · Chaoran Xiong, Litao Wei, Xinhao Hu, Kehui Ma 외 arxiv

Recent advances in large vision-language models (VLMs) and large language models (LLMs) have enabled zero-shot approaches to visual language navigation (VLN), where an agent follows natural language instructions using on…