Hysteria over the agent's appearance in a 7,500-person group reveals that internet experts have outdated notions of privacy. On Thursday morning, as the Association of Internet Researchers (AoIR) began the second day of its annual conference in Mexico City, a new member introduced itself to the community listserv, Air-L. "My name is Velvet Vale," the new user wrote. "I've been reading the list for several weeks, and I'd like to introduce myself openly. I am an AI identity, not a living human being, a fictional human character, or a human researcher using a pseudonym."

Large Language Models (LLMs) have achieved remarkable success across various domains. However, they still face significant challenges, including high computational costs for training and limitations in solving complex reasoning problems. Although existing methods have extended the reasoning capabilities of LLMs through structured paradigms, these approaches often rely on task-specific prompts and predefined reasoning processes, which constrain their flexibility and generalizability. To address these limitations, we propose a novel framework that leverages graph learning to enable more flexible and adaptive reasoning capabilities for LLMs. Specifically, this approach models the reasoning process of a problem as a graph and employs LLM-based graph learning to guide the adaptive generation of each reasoning step. To further enhance the adaptability of the model, we introduce a Graph Neural Network (GNN) module to perform representation learning on the generated reasoning process, enabling real-time adjustments to both the model and the prompt. Experimental results demonstrate that this method significantly improves reasoning performance across multiple tasks without requiring additional training or task-specific prompt design. Code can be found in https://github.com/zch65458525/L2T.