Prime Agent: A Self-Improving RLM Harness· Prime Agent：自我改进的 RLM 框架
Language models are sequential processors, but long-horizon agency requires external information and computation beyond model weights and active context. Prime Agent is an open-source harness for long-horizon evaluation and coding-agent workflows. A persistent IPython REPL follows the Recursive Language Model abstraction for programmatic context processing and test-time compute, while Continual Harness preserves histories, memories, skills, prompts, and subagent specifications across trajectories. Recursive subagents coordinate through direct agent-to-agent communication, and the Agents View lets humans inspect and manage daemon-backed sessions. Prime Agent standardizes execution, recovery, verification, and resource accounting while leaving strategy construction to the model. This low-fri
Prime Agent 为语言模型提供持久化环境，支持长期任务处理和自我改进。
- 核心方法
- Prime Agent 通过一个持久化的 IPython REPL 环境实现了对语言模型的长期任务支持，同时通过 Continual Harness 保存历史、记忆、技能、提示和子代理规范，允许递归子代理之间直接通信，并提供 Agents View 供人类监控和管理。
- 适合谁读
- 研究者 / 工程师
- 要解决的问题
- 现有语言模型在处理长期任务时缺乏外部信息和计算支持，限制了其在实际应用场景中的效能。
- 关键实验
- 未提供
- 主要贡献
- 提供了开源的长期任务评估和编码代理工作流框架，标准化了执行、恢复、验证和资源管理，增强了语言模型在复杂任务中的应用能力。
- 意义与局限
- Prime Agent 框架有望提高语言模型在长期任务中的可靠性和效率，但其实际效果还需进一步实验验证。