让AI智能提问以高效获取任务上下文，减少无效尝试。
Active Inference as Context Acquisition for AI Agents
- 用主动推断框架决定何时提问、如何提问以获取关键信息。
- 在25至300个选项的任务中，显著降低因信息缺失导致的错误率。
- 适用于需节省计算资源的智能体，尤其适合高成本场景下的对话系统。
交互式AI智能体必须高效获取正确上下文。当用户遗漏约束、偏好、文件或任务变量时，智能体可采用默认假设，或消耗资源进行澄清提问、检索、工具调用或提示测试。本文将此权衡建模为用于上下文获取的主动推断。内层推断更新对潜在任务状态的信念，外层决策选择下一步的上下文操作、任务操作或停止操作，以最小化预期自由能（含代价）。在确定性设定下，认知项简化为预期信息增益，可选地按令牌成本归一化。我们在最优提问（OQA）中实现该框架，使用精确后验与动态规划求解器，在25至300个候选项的二元与多分类任务上评估前沿语言模型。还研究了生成前澄清与令牌预算下的自动提示优化。该框架模型无关，可作为智能体上下文获取层的设计原则。
原文摘要 · Abstract (English)
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.
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。