发表机构
University of Chicago; Santa Fe Institute; Stanford University（芝加哥大学; 圣塔菲研究所; 斯坦福大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究探讨人工记忆中跨域重组，通过在两个系统实现重组重播机制，发现跨域巩固创造价值，域内排练不然，符号系统跨域连接提升显著，神经系统在特定子任务有提高，验证了相关预测，表明巩固是为发现而非记忆。
AI 中文摘要
梦将从未相遇的人、地点和时间拼接在一起。神经科学表明这种重组并非噪音，而是驱动洞察力和创造性发现的一种功能。这重新定义了记忆巩固：其可衡量的价值在于跨尚未同时发生的经历重组知识，而非仅仅防止遗忘。我们通过分离重组重播机制并在两个架构不相关的系统中实现它来直接测试这一点：一个LoRA微调管道（DREAMS）和一个重播结构化知识对象的符号引擎（SAPIENCE）。两个系统都得出相同结论：跨域巩固创造价值，而域内排练则不然。符号系统有85.7%的新跨域连接，比基线提高了21个百分点。神经系统整体提高了5.64个百分点，在明确需要跨域转移的子任务上提高了14.5个百分点。这种效应是权重的真实属性，而非提示工件。我们根据50000篇真实论文中的记录发现验证了这一预测，并陈述了一个可证伪的海马体记录预测以区分重组和排练。最终，这一原则是底物通用的，能大规模追踪真实发现。阅读文献教会模型回忆所见内容，但产生发现需要一个单独的离线阶段来跨域重组知识——做梦的计算模拟。巩固不是为了记忆，而是为了发现。
英文摘要
Dreams splice together people, places, and times that never met. Neuroscience suggests this recombination is not noise, but a function driving insight and creative discovery. This reframes memory consolidation: rather than merely defending against forgetting, its measurable value lies in recombining knowledge across experiences that have not yet co-occurred. We test this directly by isolating the recombinatory-replay mechanism and implementing it in two architecturally unrelated systems: a LoRA fine-tuning pipeline (DREAMS) and a symbolic engine replaying structured knowledge objects (SAPIENCE). Both systems converge on the same finding: cross-domain consolidation creates value, while within-domain rehearsal does not. The symbolic arm surfaces novel cross-domain connections at 85.7%, a +21 percentage point (pp) gain over baseline. The neural arm improves overall by +5.64 pp, but on subtasks explicitly requiring cross-domain transfer (like unseen math reasoning on GSM8K), gains reach +14.5 pp. This effect is a genuine property of the weights--not a prompt artifact--as prepending the same material in-context to a 671B-parameter model actually reverses the gain. We validate this prediction against documented discoveries across 50,000 real papers and state a falsifiable hippocampal-recording prediction to distinguish recombination from rehearsal. Ultimately, this principle is substrate-general, tracking real discovery at scale. Reading the literature teaches a model to recall what it has seen, but producing discovery requires a separate offline phase that recombines knowledge across domains--the computational analog of dreaming. Consolidation is not for remembering, but for discovering.
Comments38 pages, 13 figures, 7 tables
