RIDAR:以自動檢測和執行期介入保障自主研究智能體的研究誠信
RIDAR: Safeguarding Research Integrity in Autonomous Research Agents via Automated Detection and Runtime Intervention
RIDAR 論文提出一套框架,透過自動檢測及執行期間介入,識別並緩解自主研究智能體的研究誠信違規。研究提出涵蓋研究全流程 14 類違規的 RIVT;RIDAR-post-hoc 在包含 60 條專家標註軌跡的 RIV-Gold 上取得 85.2% F1,並在 RIV-Wild 的 300 條軌跡中檢出 3,964 宗違規,涉及 99.7% 軌跡。
Published on Oct 22
Authors:
,
,
,
,
,
,
,
,
Abstract
RIDAR detects and mitigates research integrity violations in autonomous agents via taxonomy-based post-hoc analysis and real-time intervention.
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.
View arXiv page View PDF GitHub Add to collection
Get this paper in your agent:
hf papers read 2610.31372
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2610.31372 in a model README.md to link it from this page.
Datasets citing this paper 1
THU-KEG/RIDAR
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2610.31372 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co