LASER: LLM Agent with State-Space Exploration for Web Navigation

• URL: http://arxiv.org/abs/2309.08172v2
• Date: Wed, 21 Feb 2024 17:42:32 GMT
• Title: LASER: LLM Agent with State-Space Exploration for Web Navigation
• Authors: Kaixin Ma, Hongming Zhang, Hongwei Wang, Xiaoman Pan, Wenhao Yu, Dong Yu
• Abstract summary: Large language models (LLMs) have been successfully adapted for interactive decision-making tasks like web navigation. Previous methods implicitly assume a forward-only execution mode for the model, where they only provide oracle trajectories as in-context examples. We propose to model the interactive task as state space exploration, where the LLM agent transitions among a pre-defined set of states by performing actions to complete the task.
• Score: 57.802977310392755
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) have been successfully adapted for interactive decision-making tasks like web navigation. While achieving decent performance, previous methods implicitly assume a forward-only execution mode for the model, where they only provide oracle trajectories as in-context examples to guide the model on how to reason in the environment. Consequently, the model could not handle more challenging scenarios not covered in the in-context examples, e.g., mistakes, leading to sub-optimal performance. To address this issue, we propose to model the interactive task as state space exploration, where the LLM agent transitions among a pre-defined set of states by performing actions to complete the task. This formulation enables flexible backtracking, allowing the model to recover from errors easily. We evaluate our proposed LLM Agent with State-Space ExploRation (LASER) on both the WebShop task and amazon.com. Experimental results show that LASER significantly outperforms previous methods and closes the gap with human performance on the web navigation task.

Related papers

• DynaSaur: Large Language Agents Beyond Predefined Actions [108.75187263724838]
  Existing LLM agent systems typically select actions from a fixed and predefined set at every step. We propose an LLM agent framework that enables the dynamic creation and composition of actions in an online manner. Our experiments on the GAIA benchmark demonstrate that this framework offers significantly greater flexibility and outperforms previous methods.
  arXiv  Detail & Related papers  (2024-11-04T02:08:59Z)
• AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web Agents [52.13695464678006]
  This study enhances an LLM-based web agent by simply refining its observation and action space. AgentOccam surpasses the previous state-of-the-art and concurrent work by 9.8 (+29.4%) and 5.9 (+15.8%) absolute points respectively.
  arXiv  Detail & Related papers  (2024-10-17T17:50:38Z)
• Are you still on track!? Catching LLM Task Drift with Activations [55.75645403965326]
  Task drift allows attackers to exfiltrate data or influence the LLM's output for other users. We show that a simple linear classifier can detect drift with near-perfect ROC AUC on an out-of-distribution test set. We observe that this approach generalizes surprisingly well to unseen task domains, such as prompt injections, jailbreaks, and malicious instructions.
  arXiv  Detail & Related papers  (2024-06-02T16:53:21Z)
• Large Language Models Can Self-Improve At Web Agent Tasks [37.17001438055515]
  Large language models (LLMs) have recently demonstrated some capability to navigate novel environments as agents in a zero-shot or few-shot fashion. We explore the extent to which LLMs can self-improve their performance as agents in long-horizon tasks in a complex environment using the WebArena benchmark. We achieve a 31% improvement in task completion rate over the base model on the WebArena benchmark through a self-improvement procedure.
  arXiv  Detail & Related papers  (2024-05-30T17:52:36Z)
• From Words to Actions: Unveiling the Theoretical Underpinnings of LLM-Driven Autonomous Systems [59.40480894948944]
  Large language model (LLM) empowered agents are able to solve decision-making problems in the physical world. Under this model, the LLM Planner navigates a partially observable Markov decision process (POMDP) by iteratively generating language-based subgoals via prompting. We prove that the pretrained LLM Planner effectively performs Bayesian aggregated imitation learning (BAIL) through in-context learning.
  arXiv  Detail & Related papers  (2024-05-30T09:42:54Z)
• Self-Exploring Language Models: Active Preference Elicitation for Online Alignment [88.56809269990625]
  We propose a bilevel objective optimistically biased towards potentially high-reward responses to actively explore out-of-distribution regions. Our experimental results demonstrate that when fine-tuned on Zephyr-7B-SFT and Llama-3-8B-Instruct models, Self-Exploring Language Models (SELM) significantly boosts the performance on instruction-following benchmarks.
  arXiv  Detail & Related papers  (2024-05-29T17:59:07Z)
• Self-Corrected Multimodal Large Language Model for End-to-End Robot Manipulation [30.54275273155153]
  Multimodal Large Language Models (MLLMs) have shown promise in visual instruction following. We introduce a Self-Corrected (SC)-MLLM, equipping our model not only to predict end-effector poses but also to autonomously recognize and correct failure actions. SC-MLLM agent significantly improve manipulation accuracy compared to previous state-of-the-art robotic MLLM (ManipLLM)
  arXiv  Detail & Related papers  (2024-05-27T17:58:48Z)
• Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as Agents [41.14201835950814]
  Large language models (LLMs) have achieved success in acting as agents, which interact with environments through tools such as search engines. Previous work has first collected interaction trajectories between LLMs and environments, using only trajectories that successfully finished the task to fine-tune smaller models. We argue that unsuccessful trajectories offer valuable insights, and LLMs can learn from these trajectories through appropriate quality control and fine-tuning strategies.
  arXiv  Detail & Related papers  (2024-02-18T17:10:07Z)
• AllTogether: Investigating the Efficacy of Spliced Prompt for Web Navigation using Large Language Models [2.234037966956278]
  We introduce AllTogether, a standardized prompt template that enhances task context representation. We evaluate the efficacy of this approach through prompt learning and instruction finetuning based on open-source Llama-2 and API-accessible GPT models.
  arXiv  Detail & Related papers  (2023-10-20T11:10:14Z)

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.