Live intelligence

Latest AI updates

1 updates
Research

When Instruction Files Go Stale: Documentation Debt and Hidden Cost in Coding Agents

The paper studies how stale repository instruction files such as AGENTS.md and CLAUDE.md affect LLM-based coding agents. Using three real-world stale instructions, 22 maintenance tasks, and 732 trajectories from two models, it finds agents follow stale guidance when it is relevant to their tasks, sometimes even when correct information is available elsewhere. On a stale test command, Claude Sonnet 5.5 needed about two extra tool calls per run compared with the corrected command, while no detectable difference appeared in the other cases. Agents generally recovered from immediate failures but did not repair the underlying instruction files.

coding agentsdocumentation debtLLM agent evaluation