Metraipolis › archive › dc_f371e2eb672a
RIDAR: Safeguarding Research Integrity in Autonomous Research Agents via Automated Detection and Runtime Intervention — arXiv:2610.31372
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.31372
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-25T20:53:24.534Z
- SHA-256 of the archived text
792e214a6ea3ea769ca4aa675ec0f44fe0cec209b861b797e7de547b0d95b70b- Stable URL of this page
https://metraipolis.com/documento/dc_f371e2eb672a
How to cite
RIDAR: Safeguarding Research Integrity in Autonomous Research Agents via Automated Detection and Runtime Intervention — arXiv:2610.31372 — arXiv (en), https://arxiv.org/abs/2610.31372 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f371e2eb672a (Metraipolis archive dc_f371e2eb672a, sha256 792e214a6ea3ea769ca4aa675ec0f44fe0cec209b861b797e7de547b0d95b70b)
BibTeX
@misc{dcf371e2eb672a,
title = {RIDAR: Safeguarding Research Integrity in Autonomous Research Agents via Automated Detection and Runtime Intervention — arXiv:2610.31372},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.31372},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f371e2eb672a; sha256 792e214a6ea3ea769ca4aa675ec0f44fe0cec209b861b797e7de547b0d95b70b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.31372. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.31372 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-25T20:47:56.930Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).