Offline Training of Language Model Agents with Functions as Learnable Weights

• URL: http://arxiv.org/abs/2402.11359v4
• Date: Tue, 30 Jul 2024 18:22:00 GMT
• Title: Offline Training of Language Model Agents with Functions as Learnable Weights
• Authors: Shaokun Zhang, Jieyu Zhang, Jiale Liu, Linxin Song, Chi Wang, Ranjay Krishna, Qingyun Wu,
• Abstract summary: We present a novel paradigm of training Large Language Models (LLMs) agents without modifying the LLM weights. We develop Agentr that employs the LLM to update agents' functions and devise an agent training algorithm with two strategies, roll-back, and early-stop. With extensive experiments, we showcase that the agent training paradigm could significantly improve the performance of representative LLM agents.
• Score: 39.88545362699836
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Researchers and practitioners have recently reframed powerful Large Language Models (LLMs) as agents, enabling them to automate complex tasks largely via the use of specialized functions. To facilitate the development of LLM agents, we present a novel paradigm of training LLM agents without modifying the LLM weights, which is particularly useful when the LLMs are difficult or inaccessible for modifications. Inspired by how humans continuously forge tools to adapt to real-world tasks, rather than change our biological structure to fit a static set of tools, we propose to progressively forge agent's functions to better solve the downstream tasks instead of modifying the LLM weights. By treating the functions as learnable `agent parameters' and leveraging the fundamental idea of model training in artificial intelligence, we develop AgentOptimizer that employs the LLM to update agents' functions and devise an agent training algorithm with two strategies, roll-back, and early-stop, to streamline the training process. With extensive experiments, we showcase that the agent training paradigm could significantly improve the performance of representative LLM agents in various downstream tasks. We also study the behavior of the agent training regarding aspects like the learning curve and domain transferability.

Related papers

• From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning [62.54484062185869]
  We introduce StepAgent, which utilizes step-wise reward to optimize the agent's reinforcement learning process. We propose implicit-reward and inverse reinforcement learning techniques to facilitate agent reflection and policy adjustment.
  arXiv  Detail & Related papers  (2024-11-06T10:35:11Z)
• SAC-GLAM: Improving Online RL for LLM agents with Soft Actor-Critic and Hindsight Relabeling [29.29604779151457]
  This paper presents and studies an adaptation of Soft Actor-Critic and hindsight relabeling to LLM agents. Our method paves the path towards autotelic LLM agents that learn online but can also outperform on-policy methods in more classic multi-goal RL environments.
  arXiv  Detail & Related papers  (2024-10-16T11:59:27Z)
• CMAT: A Multi-Agent Collaboration Tuning Framework for Enhancing Small Language Models [8.123272461141815]
  We introduce the TinyAgent model, trained on a meticulously curated high-quality dataset. We also present the Collaborative Multi-Agent Tuning (CMAT) framework, an innovative system designed to augment language agent capabilities. In this research, we propose a new communication agent framework that integrates multi-agent systems with environmental feedback mechanisms.
  arXiv  Detail & Related papers  (2024-04-02T06:07:35Z)
• Enhancing the General Agent Capabilities of Low-Parameter LLMs through Tuning and Multi-Branch Reasoning [56.82041895921434]
  Open-source pre-trained Large Language Models (LLMs) exhibit strong language understanding and generation capabilities. When used as agents for dealing with complex problems in the real world, their performance is far inferior to large commercial models such as ChatGPT and GPT-4.
  arXiv  Detail & Related papers  (2024-03-29T03:48:12Z)
• EnvGen: Generating and Adapting Environments via LLMs for Training Embodied Agents [65.38474102119181]
  We propose EnvGen, a framework to adaptively create training environments. We train a small RL agent in a mixture of the original and LLM-generated environments. We find that a small RL agent trained with EnvGen can outperform SOTA methods, including a GPT-4 agent, and learns long-horizon tasks significantly faster.
  arXiv  Detail & Related papers  (2024-03-18T17:51:16Z)
• Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization [53.510942601223626]
  Large Language Models (LLMs) exhibit robust problem-solving capabilities for diverse tasks. These task solvers necessitate manually crafted prompts to inform task rules and regulate behaviors. We propose Agent-Pro: an LLM-based Agent with Policy-level Reflection and Optimization.
  arXiv  Detail & Related papers  (2024-02-27T15:09:20Z)
• Empowering Large Language Model Agents through Action Learning [85.39581419680755]
  Large Language Model (LLM) Agents have recently garnered increasing interest yet they are limited in their ability to learn from trial and error. We argue that the capacity to learn new actions from experience is fundamental to the advancement of learning in LLM agents. We introduce a framework LearnAct with an iterative learning strategy to create and improve actions in the form of Python functions.
  arXiv  Detail & Related papers  (2024-02-24T13:13:04Z)
• Large Language Model as a Policy Teacher for Training Reinforcement Learning Agents [16.24662355253529]
  Large Language Models (LLMs) can address sequential decision-making tasks through the provision of high-level instructions. LLMs lack specialization in tackling specific target problems, particularly in real-time dynamic environments. We introduce a novel framework that addresses these challenges by training a smaller, specialized student RL agent using instructions from an LLM-based teacher agent.
  arXiv  Detail & Related papers  (2023-11-22T13:15:42Z)
• AgentTuning: Enabling Generalized Agent Abilities for LLMs [35.74502545364593]
  We present AgentTuning, a simple and general method to enhance the agent abilities of open large language models. We employ a hybrid instruction-tuning strategy by combining AgentInstruct with open-source instructions from general domains. Our evaluations show that AgentTuning enables LLMs' agent capabilities without compromising general abilities.
  arXiv  Detail & Related papers  (2023-10-19T15:19:53Z)

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.