We audited the LoCoMo benchmark (one of the most cited eval for LLM agent memory) and found 99 score-corrupting errors in 1,540 questions (6.4%). Separately, we tested the LLM judge with adversarially generated wrong answers, it accepted 62.81% of vague-but-topical wrong answers. Some published system scores barely clear that bar.
Full audit with methodology, all 99 errors documented, and reproducible scripts.
Can your plugin system support custom workflow triggers yet?