LLMs Corrupt Your Documents When You Delegate
Philippe Laban · Tobias Schnabel · Jennifer Neville
We simulate long horizon interactions between users and LLM in 52 professional domains, and find that LLMs corrupt documents when completing document editing tasks on behalf of users.
摘要
Large Language Models (LLMs) are poised to disrupt knowledge work, with the emergence of delegated work as a new interaction paradigm (e.g., vibe coding). Delegation requires trust -- the expectation that the LLM will faithfully execute the task without introducing errors into documents. We introduce DELEGATE-52 to study the readiness of AI systems in delegated workflows. DELEGATE-52 simulates long delegated workflows that require in-depth document editing across 52 professional domains, such as coding, crystallography, and music notation. Our large-scale experiment with 20 LLMs reveals that current models degrade documents during delegation: even frontier models (Gemini 3.1 Pro, GPT~5.5, Claude 4.6 Opus) corrupt an average of 22% of document content by the end of long workflows, with other models failing more severely. Additional experiments reveal that agentic tool use does not systematically improve performance on DELEGATE-52, and that degradation severity is exacerbated by document size, length of interaction, or presence of distractor files. Our analysis shows that current LLMs are unreliable delegates: they introduce sparse but severe errors that silently corrupt documents, compounding over long interaction.