MCAIR: Monitoring and Correcting Agent Unfaithfulness via Internal Representations

cs.AI, cs.LG

Submitted: 2026-10-14

Updated: 2026-10-14

Comments: 26 pages

Code: https://github.com/huggingface/smolagents

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• On the Opportunities and Risks of Foundation Models
• Discovering Latent Knowledge in Language Models Without Supervision
• INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection
• Are Your Agents Upward Deceivers?
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• OpenAI o1 System Card
• Gemma 3 Technical Report
• ATBench: A Diverse and Realistic Agent Trajectory Benchmark for Safety Evaluation and Diagnosis
• DeepSeek-V3 Technical Report
• Large Language Model Agent: A Survey on Methodology, Applications and Challenges
• The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets
• Qwen3 Technical Report
• ReAct: Synergizing Reasoning and Acting in Language Models
• Agent-SafetyBench: Evaluating the Safety of LLM Agents
• Representation Engineering: A Top-Down Approach to AI Transparency

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems