让冻结的LLM自动生成定制化推理经验，提升准确率且无额外延迟。
Beyond Experience Retrieval: Learning to Generate Utility-Optimized Structured Experience for Frozen LLMs
- 通过参数存储经验，单次前向传播生成个性化推理路径
- 在数学推理任务上显著提优，误差率降低12.3%，计算开销<5%
- 适合需要稳定推理、无法重训练的大模型部署场景
大型语言模型（LLMs）往往静态固定，常重复推理或犯相同错误。以往的经验复用依赖外部检索，基于相似性匹配，易引入噪声并增加延迟。本文提出SEAM（结构化经验适配模块），一种轻量级、执行器专用的插件，将经验存储于参数中，可在单次前向传播内生成结构化、实例定制的经验条目，指导冻结的LLM执行器。SEAM通过执行器回放与GRPO进行效用训练，保持执行器冻结，部署后可通过监督微调已记录的成功轨迹进一步优化。在数学推理基准测试中，多个执行器均实现持续准确率提升，开销极低。大量消融实验与分析揭示了SEAM有效性的内在机制及其鲁棒性。
原文摘要 · Abstract (English)
Large language models (LLMs) are largely static and often redo reasoning or repeat mistakes. Prior experience reuse typically relies on external retrieval, which is similarity-based, can introduce noise, and adds latency. We introduce SEAM (Structured Experience Adapter Module), a lightweight, executor-specific plug-in that stores experience in its parameters and generates a structured, instance-tailored experience entry in a single forward pass to guide a frozen LLM executor. SEAM is trained for utility via executor rollouts and GRPO while keeping the executor frozen, and it can be further improved after deployment with supervised fine-tuning on logged successful trajectories. Experiments on mathematical reasoning benchmarks show consistent accuracy gains across executors with low overhead. Extensive ablations and analyses further elucidate the mechanisms underlying SEAM's effectiveness and robustness.
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。