跳到正文
arXiv cs.AI· Eric Zou·· 4 小时前AI 评分26

用文本记忆智能体测试"过拟合大脑假说":LLM 会做梦吗?

Can an LLM dream? Testing the overfitted brain hypothesis on an agent with text memory

AI 导读

研究用 Claude Opus 5.5 智能体在 LongMemEval 构建的十个模拟对话日上测试 Hoel(2021)的"过拟合大脑假说",每晚按当日对话记录重写文本记忆,并对 5%–40% 的对话轮次做细节篡改或随机文本注入。

正文 · 原文

View PDF HTML (experimental)

Abstract:Hoel (2021) proposed that dreams distort replayed experience so that the brain does not overfit to recent events. We test this hypothesis on an LLM agent (Claude Opus 5.5) that stores what it learns in a text memory and rewrites that memory each night from the day's conversation transcript. The agent goes through ten simulated days of conversation built from LongMemEval. We corrupt 5, 10, 20 or 40 percent of the transcript's turns before each nightly rewrite in one of two ways. Detail corruption changes one or two details in a turn to plausible wrong ones, or replaces the turn with one by the same speaker from an earlier day. Random-text corruption replaces half of the selected turns with a passage of Moby-Dick and inserts Moby-Dick words into the other half. A size limit on the memory, rising from 19,500 to 117,000 tokens over ten nights, set from human free-recall data, forces it to forget. We learned that corruption did not help the agent apply what it learned in earlier conversations to new tasks in any of 30 runs (ten conditions, three different conversation histories). Replacing details in 40 percent of turns lowered recall from 76 to 60 percent. Random text had no consistent effect on recall, with a paired difference of 0 $\pm$ 2 points at 40 percent, because the model recognized it as corrupted and left it out of memory. Replaced details were stored as fact even when another turn held the correct value, and the agent answered 40 percent of those questions correctly, compared with 75 percent without corruption. These results suggest that a pretrained model can separate corrupted text from real events, so a fair test needs a learner that cannot make this separation as easily, such as a model fine-tuned on the corrupted days or an agent whose days take place in an invented world.
Comments: 13 pages, 7 figures, 2 tables. Code and data: this https URL
Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
Cite as: arXiv:2611.21648 [cs.CL]
  (or arXiv:2611.21648v1 [cs.CL] for this version)
  https://doi.org/10.48550/arXiv.2611.21648

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Eric Jujian Zou [view email]
[v1] Wed, 14 Oct 2026 20:44:10 UTC (104 KB)

来源:arXiv cs.AI · arxiv.org