arXiv 2610.31372 · cs.AI · 2026-10-22
RIDAR: Safeguarding Research Integrity in Autonomous Research Agents via Automated Detection and Runtime Intervention
Jiening Siow, Amy Xin, Junjie Wang, Ziyu Tang, Zijun Yao, Yunjia Qi, Fanjin Zhang, Lei Hou 等 10 人
Knowledge Engineer Group @ Tsinghua University
在最新榜 #333 本站收录于 2026-10-26
一句话要点
RIDAR 检测并干预自主科研智能体的科研诚信违规：提出 14 类违规分类，事后检测在专家标注集上 F1 达 85.2%；在 300 条真实轨迹中 99.7% 都检出违规，共 3964 处。
RIDAR detects and intervenes in research integrity violations by autonomous research agents, using a 14-type taxonomy; its post-hoc detector reaches 85.2% F1 and finds 3,964 violations in 99.7% of 300 real agent trajectories.
阅读 arXiv 原文 PDF Hugging Face 讨论 代码仓库
主题与学科
同主题：智能体
- Raven: The Harness of Harnesses for Composable Agentic Intelligence ▲748
- False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents ▲642
- Omni-IO Skills: Harnessing Your Agent Omni-Native ▲485
- BizAgentBench: Unveiling Hidden Challenges in Deploying Long-Horizon Agents for Real-World Business ▲388
- Player-1: Learning to Play from Synthetic Experience ▲347
同主题：安全与可解释
- Post-Training Leaves Behavioral Shadows on Unrelated Decisions 2026-09-24 · ▲273
- S-Space: Exploring Spatial Workspace in Multimodal Language Models 2026-10-09 · ▲270
- Right Screen, Wrong Transition: World Models as Verifiers for GUI Agents 2026-10-08 · ▲188
- Behavioral Compositionality of Sparse Autoencoder Representations 2026-10-15 · ▲108
- DecepEval: A Benchmark for Evaluating Deception in LLM Agents 2026-10-06 · ▲85
数据说明
元数据来自 arXiv API（已核实）；点赞来自 Hugging Face 每日论文；引用来自 Semantic Scholar。最近刷新 2026-10-26。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。