LLM Agents Beyond Utility: An Open-Ended Perspective
This work addresses the potential for LLM agents to achieve open-ended autonomy, which is incremental as it builds on existing agent frameworks.
The study investigated whether LLM agents can evolve from problem-solving tools into autonomous entities by enabling them to generate tasks, accumulate knowledge, and interact with their environment. The open-ended agent demonstrated capabilities like following multi-step instructions and proposing tasks, but faced limitations such as sensitivity to prompts and repetitive behavior.
Recent LLM agents have made great use of chain of thought reasoning and function calling. As their capabilities grow, an important question arises: can this software represent not only a smart problem-solving tool, but an entity in its own right, that can plan, design immediate tasks, and reason toward broader, more ambiguous goals? To study this question, we adopt an open-ended experimental setting where we augment a pretrained LLM agent with the ability to generate its own tasks, accumulate knowledge, and interact extensively with its environment. We study the resulting open-ended agent qualitatively. It can reliably follow complex multi-step instructions, store and reuse information across runs, and propose and solve its own tasks, though it remains sensitive to prompt design, prone to repetitive task generation, and unable to form self-representations. These findings illustrate both the promise and current limits of adapting pretrained LLMs toward open-endedness, and point to future directions for training agents to manage memory, explore productively, and pursue abstract long-term goals.