Year: 2024
Type: article
Abstract: Recent advancements in Large Language Models (LLMs) have expanded their application across a variety of tasks. However, open-source LLMs often fail to achieve the same efficiency as proprietary models. To address this issue, we propose Iterative Contrastive Trajectory Optimization (ICTO), a novel framework designed to enhance the task-solving capabilities of LLM-based agents. ICTO facilitates iterative learning from both successful and failed task trajectories by utilizing Partially Observable Markov Decision Processes (POMDP) to provide step-level guidance. Experimental results demonstrate that ICTO improves task-solving efficiency by 12.4% and generalization ability by 15.7% compared to baseline models. The framework not only enhances the performance of open-source LLMs but also shows promise for broader applications in autonomous learning environments.
Authors: Chengang Jing, Xin Jing, Kun Li
Institution: Xi'an Technological University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W4406687416