Large Language Model (LLM)-based agents significantly extend the utility of LLMs by interacting with dynamic environments. However, enabling agents to continually learn new tasks without catastrophic forgetting remains a critical challenge, known as the stability-plasticity dilemma. In this work, we argue that this dilemma fundamentally arises from the failure to explicitly distinguish between common knowledge shared across tasks and conflicting knowledge introduced by task-specific interference. To address this, we propose Agent-Dice, a parameter fusion framework based on directional consensus evaluation. Concretely, Agent-Dice disentangles knowledge updates through a two-stage process: geometric consensus filtering to prune conflicting gradients, and curvature-based importance weighting to amplify shared semantics. We provide a rigorous theoretical analysis that establishes the validity of the proposed fusion scheme and offers insight into the origins of the stability-plasticity dilemma. Extensive experiments on GUI agents and tool-use agent domains demonstrate that Agent-Dice exhibits outstanding continual learning performance with minimal computational overhead and parameter updates. The codes are available at https://github.com/Wuzheng02/Agent-Dice.

翻译：基于大型语言模型（LLM）的智能体通过与动态环境交互，显著扩展了LLM的实用性。然而，如何使智能体在持续学习新任务时避免灾难性遗忘仍是一个关键挑战，即稳定性-可塑性困境。本文认为，这一困境本质上源于未能明确区分任务间共享的通用知识与任务特定干扰引入的冲突知识。为解决该问题，我们提出Agent-Dice——一种基于方向性共识评估的参数融合框架。具体而言，Agent-Dice通过两阶段过程解耦知识更新：利用几何共识过滤剪除冲突梯度，并通过曲率感知的重要性加权增强共享语义。我们提供了严格的理论分析，证明了所提出融合方案的有效性，并揭示了稳定性-可塑性困境的成因。在GUI智能体与工具使用智能体领域的广泛实验表明，Agent-Dice能以极低的计算开销和参数更新量实现卓越的持续学习性能。代码已发布于https://github.com/Wuzheng02/Agent-Dice。