Abstract: Abstract：Objectives Existing unmanned surface vehicle (USV) path planning algorithms rely heavily on rule-based libraries and high-precision sensor inputs, making them ill-suited to “information-scarce” environments characterized by cognitive blind spots, perception loss, and semantic ambiguity, and thus unable to handle sudden unknown threats. This work proposes an intelligent agent framework based on large language models (LLMs) to investigate its feasibility and advantages for USV path planning under such information-scarce conditions. Methods The proposed agent framework centers on a pre-trained LLM as the planning core, integrating various tool functions (including sensor interfaces) and a human-machine interaction module, and incorporating short-term and long-term memories with both online and offline evolution capabilities. A structured prompt template is designed to organize sensor observations and their confidence levels, mission objectives, prior knowledge, decision priorities, and conditional logic into prompts that guide the LLM in environment perception, dynamic reasoning, and path generation. Results Experimental results demonstrate that, in environments with static obstacles, the proposed intelligent agent outperforms or is at least comparable to representative traditional algorithms such as A*, RRT, PSO, and Hybrid A* in key metrics including path length, number of turns, and average turning angle. The agent achieved a composite performance score of 1.00, significantly higher than those of the traditional algorithms (0.47, 0.47, 0.77, and 0.76, respectively). In dynamic environments, the LLM can effectively invoke tool functions, initiate human-in-the-loop interactions when appropriate, and perform real-time path planning based on sensor inputs. When faced with challenging conditions such as cognitive blind spots, perceptual gaps, and semantic ambiguity, the agent can adapt its planning strategy by leveraging confidence assessments, historical memory, and commonsense knowledge, demonstrating robust reasoning, generalization capabilities, and human-like intelligence. Conclusions These findings indicate that the LLM-based path planning agent exhibits significant advantages in both simple obstacle avoidance and complex, information-scarce scenarios. This approach offers strong potential to advance USVs toward higher levels of autonomy.