用可调温度的参数记忆，让语言代理生成更多样化反思，提升推理能力。
ParamMem: Augmenting Language Agents with Parametric Reflective Memory
- 将跨样本反思模式编码为参数，通过温度采样生成多样化反思。
- 在代码生成等任务上优于当前最优基线，且小模型也能有效提升性能。
- 适合需要持续自我改进的语言代理系统，尤其适用于资源受限场景。
自我反思使语言代理能够迭代优化解决方案，但常导致输出重复，限制推理效果。实证分析显示反思多样性与任务成功率呈强正相关，进一步凸显多样反思信号的重要性。我们提出ParamMem——一种参数化记忆模块，将跨样本反思模式编码至模型参数中，通过温度控制采样实现多样化反思生成。基于此模块，我们构建ParamAgent：一个融合参数化记忆、情景记忆与跨样本记忆的反思型代理框架。在代码生成、数学推理和多跳问答任务上的大量实验表明，其性能持续优于现有最先进方法。进一步分析显示，ParamMem具备样本高效性，支持从小模型到大模型的弱到强迁移，并可在无需外部更强模型的情况下实现自我提升，展现出作为增强语言代理有效组件的巨大潜力。
原文摘要 · Abstract (English)
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.
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。