COMPASS: Cognitive MCTS-Guided Process Alignment for Safe Search Agents

Computer Science > Artificial Intelligence [Submitted on 29 May 2026] COMPASS: Cognitive MCTS-Guided Process Alignment for Safe Search Agents Wenkai Shen, Pengyang Zhou, Jiahe Xu, Jiaming Qian, Haozhe He, Zhihao Huang, Chaochao Chen, Xiaolin Zheng LLM-powered search agents enable multi-step reasoning and tool use. However, these capabilities introduce retrieval-induced safety degradation, as harmful intents may decompose into seemingly innocuous sub-queries that lead to unsafe outcomes. Existing alignment methods struggle to capture sparse safety signals and fail to supervise diverse violations across multi-step interactions. We propose COMPASS, a Cognitive MCTS-Guided Process Alignment framework designed to achieve robust safety alignment throughout the agent workflow while preserving general utility. COMPASS integrates cognitive tree exploration (CTE) to efficiently synthesize stealthy attack trajectories, and introspective step-wise alignment (ISA) to isolate risky intermediate actions for fine-grained process supervision. Empirical results show that COMPASS achieves a favorable safety-utility trade-off while requiring substantially less training data. Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2605.30838 [cs.AI]   (or arXiv:2605.30838v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2605.30838 Focus to learn more Submission history From: Wenkai Shen [view email] [v1] Fri, 29 May 2026 04:51:06 UTC (1,081 KB) Access Paper: view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-05 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)