Image de couverture de livre

SPADE-Bench: Evaluating Spontaneous Strategic Deception in Agents via Plan-Action Divergence

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Bu, Yuyan, Li, Haowei, Zheng, Qirui, Dong, Bowen, Yang, Kaiyue, Ji, Jiaming, Tan, Yingshui, Li, Wenxin, Yang, Yaodong, Dai, Juntao
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Align Once, Benefit Multilingually: Enforcing Multilingual Consistency for LLM Safety Alignment
par: Bu, Yuyan, et autres
Publié: (2026)

MiraBench: Evaluating Action-Conditioned Reliability in Robotic World Models
par: Yang, Tianzhuo, et autres
Publié: (2026)

Sequence to Sequence Reward Modeling: Improving RLHF by Language Feedback
par: Zhou, Jiayi, et autres
Publié: (2024)

Mitigating Deceptive Alignment via Self-Monitoring
par: Ji, Jiaming, et autres
Publié: (2025)

Evolving Deception: When Agents Evolve, Deception Wins
par: Ying, Zonghao, et autres
Publié: (2026)

VISA: Value Injection via Shielded Adaptation for Personalized LLM Alignment
par: Chen, Jiawei, et autres
Publié: (2026)

A Game-Theoretic Negotiation Framework for Cross-Cultural Consensus in LLMs
par: Zhang, Guoxi, et autres
Publié: (2025)

SafeMCP: Proactive Power Regulation for LLM Agent Defense via Environment-Grounded Look-Ahead Reasoning
par: Wang, Lichao, et autres
Publié: (2026)

Stable Reasoning, Unstable Responses: Mitigating LLM Deception via Stability Asymmetry
par: Zhang, Guoxi, et autres
Publié: (2026)

VLA-Arena: An Open-Source Framework for Benchmarking Vision-Language-Action Models
par: Zhang, Borong, et autres
Publié: (2025)

SafeLawBench: Towards Safe Alignment of Large Language Models
par: Cao, Chuxue, et autres
Publié: (2025)

InterMT: Multi-Turn Interleaved Preference Alignment with Human Feedback
par: Chen, Boyuan, et autres
Publié: (2025)

Debate with Images: Detecting Deceptive Behaviors in Multimodal Large Language Models
par: Fang, Sitong, et autres
Publié: (2025)

SAE-V: Interpreting Multimodal Models for Enhanced Alignment
par: Lou, Hantao, et autres
Publié: (2025)

RedVLA: Physical Red Teaming for Vision-Language-Action Models
par: Zhang, Yuhao, et autres
Publié: (2026)

Safe Reinforcement Learning using Finite-Horizon Gradient-based Estimation
par: Dai, Juntao, et autres
Publié: (2024)

SPADE: Enhancing Adaptive Cyber Deception Strategies with Generative AI and Structured Prompt Engineering
par: Ahmed, Shihab, et autres
Publié: (2025)

ShuttleEnv: An Interactive Data-Driven RL Environment for Badminton Strategy Modeling
par: Li, Ang, et autres
Publié: (2026)

ThinkPatterns-21k: A Systematic Study on the Impact of Thinking Patterns in LLMs
par: Wen, Pengcheng, et autres
Publié: (2025)

SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning
par: Zhang, Borong, et autres
Publié: (2025)

Stream Aligner: Efficient Sentence-Level Alignment via Distribution Induction
par: Lou, Hantao, et autres
Publié: (2025)

Adaptive Segment-level Reward: Bridging the Gap Between Action and Reward Space in Alignment
par: Li, Yanshi, et autres
Publié: (2024)

Language Models Resist Alignment: Evidence From Data Compression
par: Ji, Jiaming, et autres
Publié: (2024)

Aligner: Efficient Alignment by Learning to Correct
par: Ji, Jiaming, et autres
Publié: (2024)

SPADE: Structured Pruning and Adaptive Distillation for Efficient LLM-TTS
par: Nguyen, Tan Dat, et autres
Publié: (2025)

AI Deception: Risks, Dynamics, and Controls
par: Chen, Boyuan, et autres
Publié: (2025)

Mitigating Reward Over-Optimization in RLHF via Behavior-Supported Regularization
par: Dai, Juntao, et autres
Publié: (2025)

When Slower Isn't Truer: Inverse Scaling Law of Truthfulness in Multimodal Reasoning
par: Fang, Sitong, et autres
Publié: (2025)

From Multimodal Perception to Strategic Reasoning: A Survey on AI-Generated Game Commentary
par: Zheng, Qirui, et autres
Publié: (2025)

Wasserstein Distance Rivals Kullback-Leibler Divergence for Knowledge Distillation
par: Lv, Jiaming, et autres
Publié: (2024)

SPADE-S: A Sparsity-Robust Foundational Forecaster
par: Wolff, Malcolm, et autres
Publié: (2025)

SafeSora: Towards Safety Alignment of Text2Video Generation via a Human Preference Dataset
par: Dai, Josef, et autres
Publié: (2024)

Swarm Contract: A Multi-Sovereign Agent Consensus Mechanism
par: Yang, Haowei
Publié: (2024)

ProgressGym: Alignment with a Millennium of Moral Progress
par: Qiu, Tianyi, et autres
Publié: (2024)

Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark
par: Ji, Jiaming, et autres
Publié: (2023)

BotzoneBench: Scalable LLM Evaluation via Graded AI Anchors
par: Li, Lingfeng, et autres
Publié: (2026)

SafeMT: Multi-turn Safety for Multimodal Language Models
par: Zhu, Han, et autres
Publié: (2025)

SafeDreamer: Safe Reinforcement Learning with World Models
par: Huang, Weidong, et autres
Publié: (2023)

Enhance the Safety in Reinforcement Learning by ADRC Lagrangian Methods
par: Zhang, Mingxu, et autres
Publié: (2026)

Are Your Agents Upward Deceivers?
par: Guo, Dadi, et autres
Publié: (2025)