计算机环境在大语言模型中激发通用代理智能
Computer Environments Elicit General Agentic Intelligence in LLMs
AI总结：
本文研究了计算机环境如何通过虚拟沙盒激发大语言模型的通用能力，展示了环境对任务解决的提升效果及训练方法。
摘要：
大语言模型中的代理智能需要模型内在能力与外部环境交互。给LLM配备计算机已成为趋势，但环境内在价值未被系统研究。本文提出LLM-in-Sandbox，将计算机虚拟化为仅有基础功能的代码沙盒，证明此最小设置能激发计算机相关的元能力：外部资源访问、文件管理与代码执行。无需额外训练，强模型在数学、物理、化学、生物医学、长上下文理解及指令遵循方面提升达15.5%，同时减少8倍的token消耗。进一步开发LLM-in-Sandbox-RL，仅在沙盒内训练模型，使弱模型能利用环境并内化交互。结果表明，计算机环境能激发通用智能，提升效率，并可通过训练利用，为通用代理提供新基础。
英文摘要：
Agentic intelligence in large language models (LLMs) requires not only model intrinsic capabilities but also interactions with external environments. Equipping LLMs with computers now represents a prevailing trend. However, the computer environment's intrinsic value has not been systematically investigated, particularly its potential to elicit general capabilities. Here we introduce LLM-in-Sandbox, which virtualizes the computer as a code sandbox with only basic functionalities, and demonstrate that this minimal setting elicits computer-based meta-capabilities for general task solving: external resource access, file management, and code execution. Without additional training, strong models achieve substantial gains (up to 15.5%) across mathematics, physics, chemistry, biomedicine, long-context understanding, and instruction following, while reducing token consumption by up to 8 times. Furthermore, we develop LLM-in-Sandbox-RL to train models exclusively on non-agentic data within the sandbox, empowering weaker models to harness the environment and internalize these interactions. Our results demonstrate that computer environments elicit general intelligence, yield efficiency gains, and can be harnessed through training, serving as a promising foundation for generalist agents.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
