一個受人類啟發的閱讀代理人，具有對非常長上下文的要點記憶。

摘要

目前的大型語言模型（LLMs）不僅受限於最大上下文長度，也無法穩健地處理長輸入。為了應對這些限制，我們提出了 ReadAgent，一個在實驗中將有效上下文長度提高了 20 倍的LLM代理系統。受到人類互動閱讀長文檔的啟發，我們將ReadAgent實現為一個簡單的提示系統，利用LLMs的高級語言能力來（1）決定將哪些內容存儲在一個記憶片段中，（2）將這些記憶片段壓縮成稱為要義記憶的短期記憶，以及（3）在需要提醒自己相關細節以完成任務時，採取查找原始文本中段落的行動。我們使用檢索方法對ReadAgent進行評估，使用原始的長上下文以及使用要義記憶。這些評估是在三個長文檔閱讀理解任務上進行的：QuALITY、NarrativeQA和QMSum。ReadAgent在所有三個任務上均優於基準線，同時將有效上下文窗口擴展了3-20倍。

English

Current Large Language Models (LLMs) are not only limited to some maximum context length, but also are not able to robustly consume long inputs. To address these limitations, we propose ReadAgent, an LLM agent system that increases effective context length up to 20x in our experiments. Inspired by how humans interactively read long documents, we implement ReadAgent as a simple prompting system that uses the advanced language capabilities of LLMs to (1) decide what content to store together in a memory episode, (2) compress those memory episodes into short episodic memories called gist memories, and (3) take actions to look up passages in the original text if ReadAgent needs to remind itself of relevant details to complete a task. We evaluate ReadAgent against baselines using retrieval methods, using the original long contexts, and using the gist memories. These evaluations are performed on three long-document reading comprehension tasks: QuALITY, NarrativeQA, and QMSum. ReadAgent outperforms the baselines on all three tasks while extending the effective context window by 3-20x.

一個受人類啟發的閱讀代理人，具有對非常長上下文的要點記憶。

A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts

摘要

Support