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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shen, Wenkai, Zhou, Pengyang, Xu, Jiahe, Qian, Jiaming, He, Haozhe, Huang, Zhihao, Chen, Chaochao, Zheng, Xiaolin
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

FOCoOp: Enhancing Out-of-Distribution Robustness in Federated Prompt Learning for Vision-Language Models
by: Liao, Xinting, et al.
Published: (2025)

FOOGD: Federated Collaboration for Both Out-of-distribution Generalization and Detection
by: Liao, Xinting, et al.
Published: (2024)

PAC-MCTS: Bias-Aware Pruning for Robust LLM-Guided Search and Planning
by: Qian, Tianhao
Published: (2026)

C-MCTS: Safe Planning with Monte Carlo Tree Search
by: Parthasarathy, Dinesh, et al.
Published: (2023)

Empirical-MCTS: Continuous Agent Evolution via Dual-Experience Monte Carlo Tree Search
by: Lu, Hao, et al.
Published: (2026)

PADER: Paillier-based Secure Decentralized Social Recommendation
by: Chen, Chaochao, et al.
Published: (2026)

ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search
by: Zhang, Dan, et al.
Published: (2024)

Exploring Explainable Multi-agent MCTS-minimax Hybrids in Board Game Using Process Mining
by: Qian, Yiyu, et al.
Published: (2025)

LoGoFair: Post-Processing for Local and Global Fairness in Federated Learning
by: Zhang, Li, et al.
Published: (2025)

PermLLM: Private Inference of Large Language Models within 3 Seconds under WAN
by: Zheng, Fei, et al.
Published: (2024)

Learning Safely Without Knowing the World:COMPASS-Hedge
by: Hu, Ting, et al.
Published: (2026)

Evaluating Cognitive Age Alignment in Interactive AI Agents
by: Shen, Yifan, et al.
Published: (2026)

I-MCTS: Enhancing Agentic AutoML via Introspective Monte Carlo Tree Search
by: Liang, Zujie, et al.
Published: (2025)

Hierarchical Multi-Agent MCTS for Safety-Critical Coordination in Mixed-Autonomy Roundabouts
by: Lin, Zhihao, et al.
Published: (2025)

COMPASS: Benchmarking Constrained Optimization in LLM Agents
by: Qin, Tian, et al.
Published: (2025)

ChatSOP: An SOP-Guided MCTS Planning Framework for Controllable LLM Dialogue Agents
by: Li, Zhigen, et al.
Published: (2024)

Rethinking the Representation in Federated Unsupervised Learning with Non-IID Data
by: Liao, Xinting, et al.
Published: (2024)

Joint Similarity Item Exploration and Overlapped User Guidance for Multi-Modal Cross-Domain Recommendation
by: Liu, Weiming, et al.
Published: (2025)

M2-PALE: A Framework for Explaining Multi-Agent MCTS--Minimax Hybrids via Process Mining and LLMs
by: Qian, Yiyu, et al.
Published: (2026)

CogMCTS: A Novel Cognitive-Guided Monte Carlo Tree Search Framework for Iterative Heuristic Evolution with Large Language Models
by: Wang, Hui, et al.
Published: (2025)

ACDZero: MCTS Agent for Mastering Automated Cyber Defense
by: Li, Yu, et al.
Published: (2026)

SafeSearch: Automated Red-Teaming of LLM-Based Search Agents
by: Dong, Jianshuo, et al.
Published: (2025)

Decoupled Competitive Framework for Semi-supervised Medical Image Segmentation
by: Chen, Jiahe, et al.
Published: (2025)

Reproducibility Companion Paper:In-processing User Constrained Dominant Sets for User-Oriented Fairness in Recommender Systems
by: Liu, Yixiu, et al.
Published: (2025)

Clinical Cognition Alignment for Gastrointestinal Diagnosis with Multimodal LLMs
by: Zheng, Huan, et al.
Published: (2026)

Bridging the Gap Between Preference Alignment and Machine Unlearning
by: Feng, Xiaohua, et al.
Published: (2025)

AMA-SAM: Adversarial Multi-Domain Alignment of Segment Anything Model for High-Fidelity Histology Nuclei Segmentation
by: Qian, Jiahe, et al.
Published: (2025)

Policy-Value Guided MDP-MCTS Framework for Cyber Kill-Chain Inference
by: Singh, Chitraksh, et al.
Published: (2025)

SafeCoT: Improving VLM Safety with Minimal Reasoning
by: Ma, Jiachen, et al.
Published: (2025)

COMPASS: A Framework for Evaluating Organization-Specific Policy Alignment in LLMs
by: Choi, Dasol, et al.
Published: (2026)

MASTER: A Multi-Agent System with LLM Specialized MCTS
by: Gan, Bingzheng, et al.
Published: (2025)

SCULPT: Constraint-Guided Pruned MCTS that Carves Efficient Paths for Mathematical Reasoning
by: Fang, Qitong, et al.
Published: (2026)

Self-Correcting RAG: Enhancing Faithfulness via MMKP Context Selection and NLI-Guided MCTS
by: Xu, Shijia, et al.
Published: (2026)

RPM-MCTS: Knowledge-Retrieval as Process Reward Model with Monte Carlo Tree Search for Code Generation
by: Lin, Yuanyuan, et al.
Published: (2025)

BiT-MCTS: A Theme-based Bidirectional MCTS Approach to Chinese Fiction Generation
by: Li, Zhaoyi, et al.
Published: (2026)

Position: Assistive Agents Need Accessibility Alignment
by: Hu, Jie, et al.
Published: (2026)

Exponential Euler method for stiff SDEs driven by fractional Brownian motion
by: Chen, Haozhe, et al.
Published: (2024)

MCTS-RAG: Enhancing Retrieval-Augmented Generation with Monte Carlo Tree Search
by: Hu, Yunhai, et al.
Published: (2025)

PhysicsAgentABM: Physics-Guided Generative Agent-Based Modeling
by: Venkatesh, Kavana, et al.
Published: (2026)

MCTS-Reasoning: Monte Carlo Tree Search for LLM Reasoning
by: Towell, Alex
Published: (2026)