On the Multi-turn Instruction Following for Conversational Web Agents

• URL: http://arxiv.org/abs/2402.15057v1
• Date: Fri, 23 Feb 2024 02:18:12 GMT
• Title: On the Multi-turn Instruction Following for Conversational Web Agents
• Authors: Yang Deng, Xuan Zhang, Wenxuan Zhang, Yifei Yuan, See-Kiong Ng, Tat-Seng Chua
• Abstract summary: We introduce a new task of Conversational Web Navigation, which necessitates sophisticated interactions that span multiple turns with both the users and the environment. We propose a novel framework, named self-reflective memory-augmented planning (Self-MAP), which employs memory utilization and self-reflection techniques.
• Score: 83.51251174629084
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Web agents powered by Large Language Models (LLMs) have demonstrated remarkable abilities in planning and executing multi-step interactions within complex web-based environments, fulfilling a wide range of web navigation tasks. Despite these advancements, the potential for LLM-powered agents to effectively engage with sequential user instructions in real-world scenarios has not been fully explored. In this work, we introduce a new task of Conversational Web Navigation, which necessitates sophisticated interactions that span multiple turns with both the users and the environment, supported by a specially developed dataset named Multi-Turn Mind2Web (MT-Mind2Web). To tackle the limited context length of LLMs and the context-dependency issue of the conversational tasks, we further propose a novel framework, named self-reflective memory-augmented planning (Self-MAP), which employs memory utilization and self-reflection techniques. Extensive experiments are conducted to benchmark the MT-Mind2Web dataset, and validate the effectiveness of the proposed method.

Related papers

• From Context to Action: Analysis of the Impact of State Representation and Context on the Generalization of Multi-Turn Web Navigation Agents [7.41862656697588]
  This study aims to analyze the various contextual elements crucial to the functioning of web navigation agents. We focus on the influence of interaction history and web page representation. Our work highlights improved agent performance across out-of-distribution scenarios.
  arXiv  Detail & Related papers  (2024-10-31T01:51:41Z)
• RA-BLIP: Multimodal Adaptive Retrieval-Augmented Bootstrapping Language-Image Pre-training [55.54020926284334]
  Multimodal Large Language Models (MLLMs) have recently received substantial interest, which shows their emerging potential as general-purpose models for various vision-language tasks. Retrieval augmentation techniques have proven to be effective plugins for both LLMs and MLLMs. In this study, we propose multimodal adaptive Retrieval-Augmented Bootstrapping Language-Image Pre-training (RA-BLIP), a novel retrieval-augmented framework for various MLLMs.
  arXiv  Detail & Related papers  (2024-10-18T03:45:19Z)
• The Compressor-Retriever Architecture for Language Model OS [20.56093501980724]
  This paper explores the concept of using a language model as the core component of an operating system (OS) A key challenge in realizing such an LM OS is managing the life-long context and ensuring statefulness across sessions. We introduce compressor-retriever, a model-agnostic architecture designed for life-long context management.
  arXiv  Detail & Related papers  (2024-09-02T23:28:15Z)
• MathChat: Benchmarking Mathematical Reasoning and Instruction Following in Multi-Turn Interactions [58.57255822646756]
  This paper introduces MathChat, a benchmark designed to evaluate large language models (LLMs) across a broader spectrum of mathematical tasks. We evaluate the performance of various SOTA LLMs on the MathChat benchmark, and we observe that while these models excel in single turn question answering, they significantly underperform in more complex scenarios. We develop MathChat sync, a synthetic dialogue based math dataset for LLM finetuning, focusing on improving models' interaction and instruction following capabilities in conversations.
  arXiv  Detail & Related papers  (2024-05-29T18:45:55Z)
• VisualWebBench: How Far Have Multimodal LLMs Evolved in Web Page Understanding and Grounding? [115.60866817774641]
  Multimodal Large Language models (MLLMs) have shown promise in web-related tasks. evaluating their performance in the web domain remains a challenge due to the lack of comprehensive benchmarks. bench is a multimodal benchmark designed to assess the capabilities of MLLMs across a variety of web tasks.
  arXiv  Detail & Related papers  (2024-04-09T02:29:39Z)
• MEIA: Multimodal Embodied Perception and Interaction in Unknown Environments [82.67236400004826]
  We introduce the Multimodal Embodied Interactive Agent (MEIA), capable of translating high-level tasks expressed in natural language into a sequence of executable actions. MEM module enables MEIA to generate executable action plans based on diverse requirements and the robot's capabilities.
  arXiv  Detail & Related papers  (2024-02-01T02:43:20Z)
• VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks [93.85005277463802]
  VisualWebArena is a benchmark designed to assess the performance of multimodal web agents on realistic tasks. To perform on this benchmark, agents need to accurately process image-text inputs, interpret natural language instructions, and execute actions on websites to accomplish user-defined objectives.
  arXiv  Detail & Related papers  (2024-01-24T18:35:21Z)
• ChatSpot: Bootstrapping Multimodal LLMs via Precise Referring Instruction Tuning [24.87615615489849]
  We present precise referring instructions that utilize diverse reference representations such as points and boxes as referring prompts to refer to the special region. We propose ChatSpot, a unified end-to-end multimodal large language model that supports diverse forms of interactivity including mouse clicks, drag-and-drop, and drawing boxes.
  arXiv  Detail & Related papers  (2023-07-18T17:56:06Z)
• Chat with the Environment: Interactive Multimodal Perception Using Large Language Models [19.623070762485494]
  Large Language Models (LLMs) have shown remarkable reasoning ability in few-shot robotic planning. Our study demonstrates that LLMs can provide high-level planning and reasoning skills and control interactive robot behavior in a multimodal environment.
  arXiv  Detail & Related papers  (2023-03-14T23:01:27Z)

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.