BACAM：面向多轮交互的行为感知持续智能体合并

中文摘要 AI 辅助

模型合并提供了一种整合各领域专家能力的方式，但现有的智能体合并方法通常要求所有专家同时可用。我们研究了持续智能体合并，即在不保留先前已合并专家的情况下，顺序整合新到来的专家。然而，在参数空间或特征子空间中进行合并并不能确保合并后的模型能够获得新专家在交互轨迹上的行为。此外，向新专家的更新可能会破坏合并模型先前整合的交互行为。因此，我们提出了行为感知持续智能体合并（BACAM），该方法利用专家引导的行为监督，从候选生成的轨迹中学习参数级别的合并门控。任务级别的稳定性-可塑性控制和张量级别的冲突感知更新预算，在允许获取新能力的同时，限制了对现有能力的干扰。学习到的门控被折叠进模型权重中，无需额外的推理时参数。在四个交互任务——网络购物、工具使用、信息检索和具身交互——中，BACAM 实现了 62.82% 的平均成功率，比评估中最强的合并基线高出 21.69 个百分点。我们的代码可在该 https URL 公开获取。

英文摘要

Model merging offers a way to integrate the capabilities of specialized experts, but existing agent merging methods typically require all of them to be available at once. We study continual agent merging, which integrates incoming experts sequentially without retaining previously merged experts. Yet merging in parameter space or feature subspaces does not ensure that the merged model acquires an incoming expert's behavior on interaction trajectories. Moreover, updates toward a new expert can disrupt the merged model's previously integrated interactive behavior. Therefore, we propose Behavior-Aware Continual Agent Merging (BACAM), which learns parameter-wise merging gates from candidate-generated trajectories using expert-guided behavioral supervision. Task-level stability-plasticity control and tensor-level conflict-aware update budgets limit interference with existing capabilities while allowing new ones to be acquired. The learned gates are folded into the model weights without additional inference-time parameters. Across four interactive tasks - web shopping, tool use, information retrieval, and embodied interaction - BACAM achieves an average success rate of 62.82%, exceeding the strongest evaluated merging baseline by 21.69 percentage points. Our code is publicly available at https://github.com/shuaitongli/BACAM.

发表机构

• School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
• Pengcheng Laboratory（鹏城实验室）
• Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）
• King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）

机构由 AI 辅助整理，请以论文原文为准。