发表机构
University of Notre Dame（圣母大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究指出知识工作成果难传承，大语言模型代理无持久记忆。提出llm-wiki-memory-template，它是异构协作知识工作基础架构，沿多人类、多代理、多领域三个轴，通过案例研究展示其能保留失败路径等，解决负面结果丢失问题。
AI 中文摘要
研究项目、教育活动及相关知识工作积累的成果、决策和推理，未来合作者难以获取。对工作最有用的部分，包括死胡同和被推翻的主张，通常被排除在出版物和共享代码之外。大语言模型编码代理虽常见，但无会话间持久记忆，基于原始来源的检索增强生成也不会累积。llm-wiki模式通过在原始来源和代理之间插入由大语言模型维护的互联维基来解决此问题。我们提出llm-wiki-memory-template，一种可复用、代理感知的实例，并认为它是异构协作知识工作的基础架构，沿三个轴（多人类、多人工智能代理、多领域），每个轴由模板的不同架构元素支持。维基按惯例只追加内容，保留失败与成功内容，解决了出版物和代码共享在结构上无法解决的负面结果丢失问题。三个已部署的案例研究和一个设计报告分别涵盖这些轴：一个保留废弃迭代的单人研究谱系；一个两作者项目，其追溯审计将两个先前实验声称的20个答案覆盖率降至14个和12个基于证据的答案，修复后又升至18个和18个，失败路径在工件中保留；一个正在进行的多代理部署设计报告；以及一个跨领域教育变体。我们将失败路径保留、代理诚实和挪用命名为工件的跨领域社会技术属性，不仅涉及其技术机制。
英文摘要
Research projects, educational efforts, and adjacent knowledge work accumulate findings, decisions, and reasoning that future collaborators rarely recover. The parts most useful to that work, including dead ends and walked-back claims, are routinely excluded from publications and shared code; future researchers re-attempt the same failures because no record survives. LLM coding agents are common participants but hold no persistent memory across sessions, and retrieval-augmented generation over raw sources does not compound. The llm-wiki pattern (Karpathy, 2026; tonbi, 2026) addresses this by inserting an LLM-maintained, interlinked wiki between raw sources and the agent. We present llm-wiki-memory-template, a reusable, agent-aware instantiation, and argue it is a substrate for heterogeneous collaborative knowledge work along three axes (multi-human, multi-AI-agent, multi-domain) with each axis supported by a distinct architectural element of the template (§4). The wiki is append-only by convention, which preserves what did not work alongside what did, addressing a negative-result loss problem that publications and code-sharing structurally cannot solve. Three deployed case studies and one design report cover the axes individually: a solo research lineage that preserves abandoned iterations; a two-author project whose retroactive audit revised two prior experiments' claimed 20-of-20 coverage down to 14 and 12 evidence-based answers, then to 18 and 18 after a fix, with the failure path preserved across the artifact; an in-progress multi-agent deployment reported as a design; and a cross-domain educational variant. We name failure-path preservation, agent honesty, and appropriation as cross-cutting sociotechnical properties of the artifact, not only of its technical mechanisms.
Comments15 pages, 3 figures, 1 table
