Enabling Intelligent Interactions between an Agent and an LLM: A Reinforcement Learning Approach

• URL: http://arxiv.org/abs/2306.03604v7
• Date: Wed, 19 Jun 2024 06:22:25 GMT
• Title: Enabling Intelligent Interactions between an Agent and an LLM: A Reinforcement Learning Approach
• Authors: Bin Hu, Chenyang Zhao, Pu Zhang, Zihao Zhou, Yuanhang Yang, Zenglin Xu, Bin Liu,
• Abstract summary: Large language models (LLMs) encode a vast amount of world knowledge acquired from massive text datasets. LLMs can assist an embodied agent in solving complex sequential decision making tasks by providing high-level instructions. We propose When2Ask, a reinforcement learning based approach that learns when it is necessary to query LLMs for high-level instructions.
• Score: 31.6589518077397
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Large language models (LLMs) encode a vast amount of world knowledge acquired from massive text datasets. Recent studies have demonstrated that LLMs can assist an embodied agent in solving complex sequential decision making tasks by providing high-level instructions. However, interactions with LLMs can be time-consuming. In many practical scenarios, it requires a significant amount of storage space that can only be deployed on remote cloud servers. Additionally, using commercial LLMs can be costly since they may charge based on usage frequency. In this paper, we explore how to enable intelligent cost-effective interactions between a down stream task oriented agent and an LLM. We find that this problem can be naturally formulated by a Markov decision process (MDP), and propose When2Ask, a reinforcement learning based approach that learns when it is necessary to query LLMs for high-level instructions to accomplish a target task. One one side, When2Ask discourages unnecessary redundant interactions, while on the other side, it enables the agent to identify and follow useful instructions from the LLM. This enables the agent to halt an ongoing plan and transition to a more suitable one based on new environmental observations. Experiments on MiniGrid and Habitat environments that entail planning sub-goals demonstrate that When2Ask learns to solve target tasks with only a few necessary interactions with the LLM, significantly reducing interaction costs in testing environments compared with baseline methods. Our code is available at: https://github.com/ZJLAB-AMMI/LLM4RL.

Related papers

• AGILE: A Novel Reinforcement Learning Framework of LLM Agents [7.982249117182315]
  We introduce a novel reinforcement learning framework of LLM agents designed to perform complex conversational tasks with users. The agent possesses capabilities beyond conversation, including reflection, tool usage, and expert consultation. Our experiments show that AGILE agents based on 7B and 13B LLMs trained with PPO can outperform GPT-4 agents.
  arXiv  Detail & Related papers  (2024-05-23T16:17:44Z)
• Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration [70.09561665520043]
  We propose a novel framework for multi-agent collaboration that introduces Reinforced Advantage feedback (ReAd) for efficient self-refinement of plans. We provide theoretical analysis by extending advantage-weighted regression in reinforcement learning to multi-agent systems. Experiments on Over-AI and a difficult variant of RoCoBench show that ReAd surpasses baselines in success rate, and also significantly decreases the interaction steps of agents.
  arXiv  Detail & Related papers  (2024-05-23T08:33:19Z)
• Sub-goal Distillation: A Method to Improve Small Language Agents [21.815417165548187]
  Large Language Models (LLMs) have demonstrated significant promise as agents in interactive tasks. We propose a method for transferring the performance of an LLM with billions of parameters to a much smaller language model. In ScienceWorld, a challenging and multi-task interactive text environment, our method surpasses standard imitation learning based solely on elementary actions by 16.7%.
  arXiv  Detail & Related papers  (2024-05-04T20:34:06Z)
• Knowledgeable Agents by Offline Reinforcement Learning from Large Language Model Rollouts [10.929547354171723]
  This paper introduces Knowledgeable Agents from Language Model Rollouts (KALM) It extracts knowledge from large language models (LLMs) in the form of imaginary rollouts that can be easily learned by the agent through offline reinforcement learning methods. It achieves a success rate of 46% in executing tasks with unseen goals, substantially surpassing the 26% success rate achieved by baseline methods.
  arXiv  Detail & Related papers  (2024-04-14T13:19:40Z)
• Small Models, Big Insights: Leveraging Slim Proxy Models To Decide When and What to Retrieve for LLMs [60.40396361115776]
  This paper introduces a novel collaborative approach, namely SlimPLM, that detects missing knowledge in large language models (LLMs) with a slim proxy model. We employ a proxy model which has far fewer parameters, and take its answers as answers. Heuristic answers are then utilized to predict the knowledge required to answer the user question, as well as the known and unknown knowledge within the LLM.
  arXiv  Detail & Related papers  (2024-02-19T11:11:08Z)
• LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models [56.25156596019168]
  This paper introduces the LMRL-Gym benchmark for evaluating multi-turn RL for large language models (LLMs) Our benchmark consists of 8 different language tasks, which require multiple rounds of language interaction and cover a range of tasks in open-ended dialogue and text games.
  arXiv  Detail & Related papers  (2023-11-30T03:59:31Z)
• LLM Augmented Hierarchical Agents [4.574041097539858]
  Solving long-horizon, temporally-extended tasks using Reinforcement Learning (RL) is challenging, compounded by the common practice of learning without prior knowledge (or tabula rasa learning) In this paper we exploit the planning capabilities of LLMs while using RL to provide learning from the environment, resulting in a hierarchical agent that uses LLMs to solve long-horizon tasks. This approach is evaluated in simulation environments such as MiniGrid, SkillHack, and Crafter, and on a real robot arm in block manipulation tasks.
  arXiv  Detail & Related papers  (2023-11-09T18:54:28Z)
• Dynamic Planning with a LLM [15.430182858130884]
  Large Language Models (LLMs) can solve many NLP tasks in zero-shot settings, but applications involving embodied agents remain problematic. Our work presents LLM Dynamic Planner (LLM-DP), a neuro-symbolic framework where an LLM works hand-in-hand with a traditional planner to solve an embodied task.
  arXiv  Detail & Related papers  (2023-08-11T21:17:13Z)
• AgentBench: Evaluating LLMs as Agents [88.45506148281379]
  Large Language Models (LLMs) are becoming increasingly smart and autonomous, targeting real-world pragmatic missions beyond traditional NLP tasks. We present AgentBench, a benchmark that currently consists of 8 distinct environments to assess LLM-as-Agent's reasoning and decision-making abilities.
  arXiv  Detail & Related papers  (2023-08-07T16:08:11Z)
• Low-code LLM: Graphical User Interface over Large Language Models [115.08718239772107]
  This paper introduces a novel human-LLM interaction framework, Low-code LLM. It incorporates six types of simple low-code visual programming interactions to achieve more controllable and stable responses. We highlight three advantages of the low-code LLM: user-friendly interaction, controllable generation, and wide applicability.
  arXiv  Detail & Related papers  (2023-04-17T09:27:40Z)
• Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback [127.75419038610455]
  Large language models (LLMs) are able to generate human-like, fluent responses for many downstream tasks. This paper proposes a LLM-Augmenter system, which augments a black-box LLM with a set of plug-and-play modules.
  arXiv  Detail & Related papers  (2023-02-24T18:48:43Z)

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.