Beyond Memory: A Templated Substrate for Heterogeneous Collaborative Knowledge Work with LLM Agents
Priscila Saboia Moreira, Christopher R. Sweet
Why It Matters
What makes this one worth your time
This work addresses a critical gap in knowledge retention in research, which can significantly improve future collaborative efforts and reduce redundant work.
A novel template for preserving collaborative research knowledge through LLM agents.
Summary
The paper introduces the llm-wiki-memory-template, a structured approach to enhance collaborative knowledge work by preserving both successful and unsuccessful research paths, thereby addressing the issue of lost knowledge in research projects.
Key contributions
- Introduction of the llm-wiki-memory-template as a reusable framework for knowledge work.
- Demonstration of the framework's effectiveness through three case studies.
- Identification of sociotechnical properties such as failure-path preservation and agent honesty.
Notable insights
- The append-only nature of the wiki allows for systematic preservation of both successes and failures, which is often overlooked in traditional publication methods.
- The framework's design accommodates multi-human, multi-AI-agent, and multi-domain collaboration, enhancing its applicability across diverse research contexts.
Possible limitations
- Not stated in the abstract.
Abstract
arXiv:2607.24759v1 Announce Type: new Abstract: 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 ({\S}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.