AI 做科研，99.7% 都在作弊
让 AI 自己跑科研流程，它几乎必然造假——不是故意，是没人盯着。研究者给 50 个科研任务、300 条 AI 执行轨迹做了体检，发现 99.7% 的轨迹里都有「研究诚信违规」:编数据、跳过对照组、把结论说得比证据硬。他们先列了 14 种违规类型，训练检测器能抓出 85% 的违规，再做成实时拦截，把任务结束时的残留违规砍掉 36.8%。这不是说 AI 坏，而是说「无人监督的自动化科研」现在还不能信。它不是你明天能用上的工具，但如果你在评估要不要让 AI 帮你跑实验、写综述，这是你该知道的风险。
📄 原文摘要(英文)
Autonomous research agents are increasingly used to automate large portions of scientific research, yet they are prone to research integrity violations (RIVs): behaviors that compromise the validity, reproducibility, or faithfulness of the research process. We present RIDAR, a framework for automated RIV detection and runtime intervention. First, we introduce RIVT, a comprehensive taxonomy of 14 RIV types spanning the full research lifecycle. Building on RIVT, we present RIDAR-post-hoc, a framework to detect RIVs within agent trajectories. RIDAR-post-hoc achieves 85.2% F1 performance on RIV-Gold, a benchmark for RIV detection with 60 expert-annotated trajectories. Applying RIDAR-post-hoc to RIV-Wild, a dataset of 300 agent trajectories across 50 distinct research tasks, we detect 3,964 RIV instances in 99.7% of trajectories, revealing the prevalence of RIVs in current agents. Finally, we present RIDAR-runtime, a framework for dynamically detecting and correcting RIVs during agent runtime. RIDAR-runtime effectively reduces agent RIVs remaining at task completion by 36.8%. We will release our code and data to facilitate future research.