主动推理作为AI智能体的上下文获取机制
Active Inference as Context Acquisition for AI Agents
查看机构详情
- University of California, Davis（加利福尼亚大学戴维斯分校）
- Technical University of Munich（慕尼黑工业大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
该研究将AI智能体的上下文获取权衡形式化为主动推理，在最优提问框架中验证其有效性，为智能体上下文获取层提供模型无关的设计原则。
中文摘要 AI 辅助
交互式AI智能体必须尽可能高效地获取正确上下文。当用户省略约束、偏好、文件或任务变量时，智能体可采用默认假设，或花费token进行澄清提问、检索调用、工具调用或提示词尝试。我们将该权衡问题形式化为上下文获取的主动推理：内部推理步骤更新对潜在任务状态的信念，外部决策选择下一个上下文动作、任务动作或停止动作，以最小化成本下的预期自由能。在确定性设置中，认知项简化为预期信息增益，可按token成本归一化。我们在最优提问（Optimal Question Asking, OQA）中实例化该框架，采用精确后验和动态规划神谕，在25至300个候选的二元和多分类任务上对前沿语言模型进行基准测试。我们还研究生成前的澄清及token预算下的自动提示优化。该形式化与模型无关，将主动推理视为AI智能体上下文获取层的设计原则。
英文摘要
Interactive AI agents must acquire the right context as efficiently as possible. When a user omits a constraint, preference, file, or task variable, an agent can proceed with a default assumption or spend tokens on a clarifying question, retrieval call, tool call, or prompt trial. We formulate this tradeoff as active inference for context acquisition. An inner inference step updates beliefs over a latent task state, and an outer decision selects the next context action, task action, or stop action to minimize expected free energy under cost. In deterministic settings, the epistemic term reduces to expected information gain, optionally normalized by token cost. We instantiate the framework in Optimal Question Asking (OQA), with exact posteriors and a dynamic programming oracle, and benchmark frontier language models on binary and multiway categorical tasks from 25 to 300 candidates. We also study clarification before generation and automated prompt optimization under token budgets. The formulation is model-agnostic and views active inference as a design principle for the context-acquisition layer of AI agents.
