让大模型不只是解题，而是能自主设目标、存记忆、持续探索。
LLM Agents Beyond Utility: An Open-Ended Perspective
- 让大模型自动生成任务并积累知识，突破固定指令限制。
- 能执行多步复杂指令，跨会话复用信息，但易重复生成任务。
- 适合研究开放性智能体与长期目标规划的未来方向。
近期的大语言模型代理已广泛使用思维链推理和函数调用。随着能力提升，一个关键问题浮现：这类软件能否不仅是智能求解工具，更成为具备自主规划、设计即时任务并朝向更模糊长远目标推理的独立实体？为研究此问题，我们采用开放性实验设置，增强预训练大模型代理的自我任务生成、知识积累与环境交互能力。定性研究表明，该代理可稳定执行复杂多步指令，跨运行存储并复用信息，主动提出并解决自身任务；但仍受提示设计影响，易重复生成任务，且无法形成自我表征。这些发现揭示了将预训练大模型转向开放性的潜力与当前局限，指明未来在记忆管理、有效探索及抽象长期目标追求方面的训练方向。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。