Multi-agent Planning using Visual Language Models

• URL: http://arxiv.org/abs/2408.05478v1
• Date: Sat, 10 Aug 2024 08:10:17 GMT
• Title: Multi-agent Planning using Visual Language Models
• Authors: Michele Brienza, Francesco Argenziano, Vincenzo Suriani, Domenico D. Bloisi, Daniele Nardi,
• Abstract summary: Large Language Models (LLMs) and Visual Language Models (VLMs) are attracting increasing interest due to their improving performance and applications across various domains and tasks. LLMs andVLMs can produce erroneous results, especially when a deep understanding of the problem domain is required. We propose a multi-agent architecture for embodied task planning that operates without the need for specific data structures as input.
• Score: 2.2369578015657954
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) and Visual Language Models (VLMs) are attracting increasing interest due to their improving performance and applications across various domains and tasks. However, LLMs and VLMs can produce erroneous results, especially when a deep understanding of the problem domain is required. For instance, when planning and perception are needed simultaneously, these models often struggle because of difficulties in merging multi-modal information. To address this issue, fine-tuned models are typically employed and trained on specialized data structures representing the environment. This approach has limited effectiveness, as it can overly complicate the context for processing. In this paper, we propose a multi-agent architecture for embodied task planning that operates without the need for specific data structures as input. Instead, it uses a single image of the environment, handling free-form domains by leveraging commonsense knowledge. We also introduce a novel, fully automatic evaluation procedure, PG2S, designed to better assess the quality of a plan. We validated our approach using the widely recognized ALFRED dataset, comparing PG2S to the existing KAS metric to further evaluate the quality of the generated plans.

Related papers

• AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML [56.565200973244146]
  Automated machine learning (AutoML) accelerates AI development by automating tasks in the development pipeline. Recent works have started exploiting large language models (LLM) to lessen such burden. This paper proposes AutoML-Agent, a novel multi-agent framework tailored for full-pipeline AutoML.
  arXiv  Detail & Related papers  (2024-10-03T20:01:09Z)
• ET-Plan-Bench: Embodied Task-level Planning Benchmark Towards Spatial-Temporal Cognition with Foundation Models [39.606908488885125]
  ET-Plan-Bench is a benchmark for embodied task planning using Large Language Models (LLMs) It features a controllable and diverse set of embodied tasks varying in different levels of difficulties and complexities. Our benchmark distinguishes itself as a large-scale, quantifiable, highly automated, and fine-grained diagnostic framework.
  arXiv  Detail & Related papers  (2024-10-02T19:56:38Z)
• BabelBench: An Omni Benchmark for Code-Driven Analysis of Multimodal and Multistructured Data [61.936320820180875]
  Large language models (LLMs) have become increasingly pivotal across various domains. BabelBench is an innovative benchmark framework that evaluates the proficiency of LLMs in managing multimodal multistructured data with code execution. Our experimental findings on BabelBench indicate that even cutting-edge models like ChatGPT 4 exhibit substantial room for improvement.
  arXiv  Detail & Related papers  (2024-10-01T15:11:24Z)
• Towards Human-Level Understanding of Complex Process Engineering Schematics: A Pedagogical, Introspective Multi-Agent Framework for Open-Domain Question Answering [0.0]
  In the chemical and process industries, Process Flow Diagrams (PFDs) and Piping and Instrumentation Diagrams (P&IDs) are critical for design, construction, and maintenance. Recent advancements in Generative AI have shown promise in understanding and interpreting process diagrams for Visual Question Answering (VQA) We propose a secure, on-premises enterprise solution using a hierarchical, multi-agent Retrieval Augmented Generation (RAG) framework.
  arXiv  Detail & Related papers  (2024-08-24T19:34:04Z)
• Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More? [54.667202878390526]
  Long-context language models (LCLMs) have the potential to revolutionize our approach to tasks traditionally reliant on external tools like retrieval systems or databases. We introduce LOFT, a benchmark of real-world tasks requiring context up to millions of tokens designed to evaluate LCLMs' performance on in-context retrieval and reasoning. Our findings reveal LCLMs' surprising ability to rival state-of-the-art retrieval and RAG systems, despite never having been explicitly trained for these tasks.
  arXiv  Detail & Related papers  (2024-06-19T00:28:58Z)
• Unlocking Large Language Model's Planning Capabilities with Maximum Diversity Fine-tuning [10.704716790096498]
  Large language models (LLMs) have demonstrated impressive task-solving capabilities, achieved through either prompting techniques or system designs. This paper investigates the impact of fine-tuning on LLMs' planning capabilities. We propose the Maximum Diversity Fine-Tuning (MDFT) strategy to improve the sample efficiency of fine-tuning in the planning domain.
  arXiv  Detail & Related papers  (2024-06-15T03:06:14Z)
• PosterLLaVa: Constructing a Unified Multi-modal Layout Generator with LLM [58.67882997399021]
  Our research introduces a unified framework for automated graphic layout generation. Our data-driven method employs structured text (JSON format) and visual instruction tuning to generate layouts. We conduct extensive experiments and achieved state-of-the-art (SOTA) performance on public multi-modal layout generation benchmarks.
  arXiv  Detail & Related papers  (2024-06-05T03:05:52Z)
• Dial-insight: Fine-tuning Large Language Models with High-Quality Domain-Specific Data Preventing Capability Collapse [4.98050508891467]
  We propose a two-stage approach for the construction of production prompts designed to yield high-quality data. This method involves the generation of a diverse array of prompts that encompass a broad spectrum of tasks and exhibit a rich variety of expressions. We introduce a cost-effective, multi-dimensional quality assessment framework to ensure the integrity of the generated labeling data.
  arXiv  Detail & Related papers  (2024-03-14T08:27:32Z)
• Adapting Large Language Models for Content Moderation: Pitfalls in Data Engineering and Supervised Fine-tuning [79.53130089003986]
  Large Language Models (LLMs) have become a feasible solution for handling tasks in various domains. In this paper, we introduce how to fine-tune a LLM model that can be privately deployed for content moderation.
  arXiv  Detail & Related papers  (2023-10-05T09:09:44Z)
• Optimal Event Monitoring through Internet Mashup over Multivariate Time Series [77.34726150561087]
  This framework supports the services of model definitions, querying, parameter learning, model evaluations, data monitoring, decision recommendations, and web portals. We further extend the MTSA data model and query language to support this class of problems for the services of learning, monitoring, and recommendation.
  arXiv  Detail & Related papers  (2022-10-18T16:56:17Z)
• An Empirical Evaluation of Flow Based Programming in the Machine Learning Deployment Context [11.028123436097616]
  Data Oriented Architecture (DOA) is an emerging approach that can support data scientists and software developers when addressing challenges. This paper proposes to consider Flow-Based Programming (FBP) as a paradigm for creating DOA applications. We empirically evaluate FBP in the context of ML deployment on four applications that represent typical data science projects.
  arXiv  Detail & Related papers  (2022-04-27T09:08:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.