DecepEval: A Benchmark for Evaluating Deception in LLM Agents

arXiv:2610.07967 · cs.LG · Submitted 2026-10-06 · Read on arXiv

cs.LG

Submitted: 2026-10-06

Updated: 2026-10-06

Code: https://github.com/functy/DECEPEVAL

Terminology

• Benchmark — 1× in this paper · explained in 2 episodes

Sources

• Constitutional AI: Harmlessness from AI Feedback
• BeHonest: Benchmarking Honesty in Large Language Models
• The Traitors: Deception and Trust in Multi-Agent Language Model Simulations
• DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
• Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks
• Are Your Agents Upward Deceivers?
• Uncovering Deceptive Tendencies in Language Models: A Simulated Company AI Assistant
• The Road to Artificial SuperIntelligence: A Comprehensive Survey of Superalignment
• Frontier Models are Capable of In-context Scheming

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks