ParamMem: 通过参数化反思记忆增强语言代理
ParamMem: Augmenting Language Agents with Parametric Reflective Memory
AI总结:
ParamMem通过参数化记忆模块提升语言代理的反思多样性,实现更高效的推理和跨任务迁移能力。
摘要:
自我反思使语言代理能够迭代地优化解决方案,但通常会产生重复的输出,从而限制推理性能。最近的研究尝试通过各种方法解决这一限制,其中增加反思多样性显示出前景。我们的实证分析揭示了反思多样性和任务成功率之间存在强烈的正相关性,进一步激发了对多样化反思信号的需求。我们引入了ParamMem,一种参数化记忆模块,将跨样本的反思模式编码到模型参数中,通过温度控制采样实现多样化反思生成。在此模块基础上,我们提出了ParamAgent,一种基于反思的代理框架,将参数化记忆与事件性和跨样本记忆相结合。在代码生成、数学推理和多跳问答等任务上的大量实验显示,与最先进的基线相比,表现一致地得到提升。进一步分析表明,ParamMem在样本效率方面表现良好,能够在不同模型规模之间实现弱到强的迁移,并且支持在不依赖更强外部模型的情况下进行自我改进,突显了ParamMem作为增强语言代理的有效组件的潜力。
英文摘要:
Self-reflection enables language agents to iteratively refine solutions, yet often produces repetitive outputs that limit reasoning performance. Recent studies have attempted to address this limitation through various approaches, among which increasing reflective diversity has shown promise. Our empirical analysis reveals a strong positive correlation between reflective diversity and task success, further motivating the need for diverse reflection signals. We introduce ParamMem, a parametric memory module that encodes cross-sample reflection patterns into model parameters, enabling diverse reflection generation through temperature-controlled sampling. Building on this module, we propose ParamAgent, a reflection-based agent framework that integrates parametric memory with episodic and cross-sample memory. Extensive experiments on code generation, mathematical reasoning, and multi-hop question answering demonstrate consistent improvements over state-of-the-art baselines. Further analysis reveals that ParamMem is sample-efficient, enables weak-to-strong transfer across model scales, and supports self-improvement without reliance on stronger external model, highlighting the potential of ParamMem as an effective component for enhancing language agents.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。