LLM agents have rapidly evolved into autonomous systems, yet a persistent information gap remains between users and agents: communication is costly, while users' identical preferences further limit information exchange. To investigate how agents should communicate across modalities, this paper formalizes Communication Policy, establishes textual and UI-based policies, and then evaluates communication policies across diverse environments, personas, and model combinations. Building information asymmetry for proactive agents, we set up two complementary settings, User-Agent and Planner-Executor. Experimental results reveal complementary strengths between interaction channels: text-based interaction often facilitates task performance, while structured UI improves agents' response quality and persona compliance. Motivated by that, a hybrid method combines these advantages. We further propose Communication Policy Evolution (CPE), a self-evolution framework for refining communication policies through rollout and prompt-level evolving. Without model modification, CPE achieves the best task success across multiple settings using prompt refinement alone. Our findings identify communication behavior as a critical yet underexplored design dimension for LLM agents.

翻译：大语言模型代理已迅速演变为自主系统，但用户与代理之间仍存在持续的信息鸿沟：通信成本高昂，而用户偏好的同质化进一步限制了信息交换。为探究代理应如何跨模态进行通信，本文形式化定义了通信策略，建立了基于文本和用户界面的策略，并在多样化环境、角色设定及模型组合下评估了这些通信策略。为构建面向主动型代理的信息不对称，我们设置了两个互补场景：用户-代理与规划者-执行者。实验揭示了交互渠道间的互补优势：基于文本的交互通常有助于提升任务性能，而结构化用户界面则能改善代理的响应质量及对角色设定的遵循度。受此启发，我们提出了一种融合两者优势的混合方法。本文进一步提出了通信策略演进（CPE），这是一种通过策略展开和提示层面演化来优化通信策略的自我演进框架。在不修改模型的情况下，CPE仅通过提示优化便在多个场景中实现了最佳任务成功率。我们的发现将通信行为识别为大语言模型代理一个关键但尚未充分探索的设计维度。