Investigate-Consolidate-Exploit: A General Strategy for Inter-Task Agent
Self-Evolution
- URL: http://arxiv.org/abs/2401.13996v1
- Date: Thu, 25 Jan 2024 07:47:49 GMT
- Title: Investigate-Consolidate-Exploit: A General Strategy for Inter-Task Agent
Self-Evolution
- Authors: Cheng Qian, Shihao Liang, Yujia Qin, Yining Ye, Xin Cong, Yankai Lin,
Yesai Wu, Zhiyuan Liu, Maosong Sun
- Abstract summary: Investigate-Consolidate-Exploit (ICE) is a novel strategy for enhancing the adaptability and flexibility of AI agents.
ICE promotes the transfer of knowledge between tasks for genuine self-evolution.
Our experiments on the XAgent framework demonstrate ICE's effectiveness, reducing API calls by as much as 80%.
- Score: 92.84441068115517
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: This paper introduces Investigate-Consolidate-Exploit (ICE), a novel strategy
for enhancing the adaptability and flexibility of AI agents through inter-task
self-evolution. Unlike existing methods focused on intra-task learning, ICE
promotes the transfer of knowledge between tasks for genuine self-evolution,
similar to human experience learning. The strategy dynamically investigates
planning and execution trajectories, consolidates them into simplified
workflows and pipelines, and exploits them for improved task execution. Our
experiments on the XAgent framework demonstrate ICE's effectiveness, reducing
API calls by as much as 80% and significantly decreasing the demand for the
model's capability. Specifically, when combined with GPT-3.5, ICE's performance
matches that of raw GPT-4 across various agent tasks. We argue that this
self-evolution approach represents a paradigm shift in agent design,
contributing to a more robust AI community and ecosystem, and moving a step
closer to full autonomy.
Related papers
- Tradeoffs When Considering Deep Reinforcement Learning for Contingency Management in Advanced Air Mobility [0.0]
Air transportation is undergoing a rapid evolution globally with the introduction of Advanced Air Mobility (AAM)
Increased levels of automation are likely necessary to achieve operational safety and efficiency goals.
This paper explores the use of Deep Reinforcement Learning (DRL) which has shown promising performance in complex and high-dimensional environments.
arXiv Detail & Related papers (2024-06-28T19:09:55Z) - Learning to Transfer for Evolutionary Multitasking [30.01466615418299]
Evolutionary multitasking (EMT) is an emerging approach for solving multitask optimization problems (MTOPs)
Current approaches in implicit EMT face challenges in adaptability, due to the use of a limited number of evolution operators.
We propose a novel Learning to Transfer (L2T) framework to automatically discover efficient KT policies for the MTOPs.
arXiv Detail & Related papers (2024-06-20T14:31:24Z) - Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement [50.481380478458945]
Iterative step-level Process Refinement (IPR) framework provides detailed step-by-step guidance to enhance agent training.
Our experiments on three complex agent tasks demonstrate that our framework outperforms a variety of strong baselines.
arXiv Detail & Related papers (2024-06-17T03:29:13Z) - Diffusion-Reinforcement Learning Hierarchical Motion Planning in Adversarial Multi-agent Games [6.532258098619471]
We focus on a motion planning task for an evasive target in a partially observable multi-agent adversarial pursuit-evasion games (PEG)
These pursuit-evasion problems are relevant to various applications, such as search and rescue operations and surveillance robots.
We propose a hierarchical architecture that integrates a high-level diffusion model to plan global paths responsive to environment data.
arXiv Detail & Related papers (2024-03-16T03:53:55Z) - Decentralized and Lifelong-Adaptive Multi-Agent Collaborative Learning [57.652899266553035]
Decentralized and lifelong-adaptive multi-agent collaborative learning aims to enhance collaboration among multiple agents without a central server.
We propose DeLAMA, a decentralized multi-agent lifelong collaborative learning algorithm with dynamic collaboration graphs.
arXiv Detail & Related papers (2024-03-11T09:21:11Z) - Dynamic LLM-Agent Network: An LLM-agent Collaboration Framework with
Agent Team Optimization [59.39113350538332]
Large language model (LLM) agents have been shown effective on a wide range of tasks, and by ensembling multiple LLM agents, their performances could be further improved.
Existing approaches employ a fixed set of agents to interact with each other in a static architecture.
We build a framework named Dynamic LLM-Agent Network ($textbfDyLAN$) for LLM-agent collaboration on complicated tasks like reasoning and code generation.
arXiv Detail & Related papers (2023-10-03T16:05:48Z) - ProAgent: Building Proactive Cooperative Agents with Large Language
Models [89.53040828210945]
ProAgent is a novel framework that harnesses large language models to create proactive agents.
ProAgent can analyze the present state, and infer the intentions of teammates from observations.
ProAgent exhibits a high degree of modularity and interpretability, making it easily integrated into various coordination scenarios.
arXiv Detail & Related papers (2023-08-22T10:36:56Z) - A Surrogate-Assisted Controller for Expensive Evolutionary Reinforcement
Learning [14.128178683323108]
In this work, we propose Surrogate-assisted Controller (SC), a novel and efficient module that can be integrated into existing frameworks.
The key challenge is to prevent the optimization process from being misled by the possible false minima introduced by the surrogate.
Experiments on six continuous control tasks from the OpenAI Gym platform show that SC can not only significantly reduce the cost of fitness evaluations, but also boost the performance of the original hybrid frameworks.
arXiv Detail & Related papers (2022-01-01T06:42:51Z) - Meta Reinforcement Learning with Autonomous Inference of Subtask
Dependencies [57.27944046925876]
We propose and address a novel few-shot RL problem, where a task is characterized by a subtask graph.
Instead of directly learning a meta-policy, we develop a Meta-learner with Subtask Graph Inference.
Our experiment results on two grid-world domains and StarCraft II environments show that the proposed method is able to accurately infer the latent task parameter.
arXiv Detail & Related papers (2020-01-01T17:34:00Z)
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.