Learning Steganography Is Easy, Learning Steganographic Reasoning Is Hard

arXiv:2609.39838 · cs.AI, cs.CL, cs.LG · Submitted 2026-09-30 · Read on arXiv

cs.AI, cs.CL, cs.LG

Submitted: 2026-09-30

Updated: 2026-09-30

Code: https://github.com/stegano-ai/steg-reasoning-is-hard

Terminology

• Accuracy — 91× in this paper · explained in 1 episode
• Trace — 48× in this paper · explained in 2 episodes
• In-Context Learning — 15× in this paper · explained in 4 episodes
• Decode — 13× in this paper · explained in 2 episodes
• Fine-Tuning — 8× in this paper · explained in 5 episodes
• Reinforcement Learning — 5× in this paper · explained in 4 episodes
• Transformer — 4× in this paper · explained in 2 episodes
• GRPO — 3× in this paper · explained in 6 episodes
• Thinking mode — 2× in this paper · explained in 2 episodes
• Agentic Coding — 1× in this paper · explained in 1 episode
• Agentic Reasoning — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes

Sources

• Chain-of-Thought Reasoning In The Wild Is Not Always Faithful
• CoT Red-Handed: Stress Testing Chain-of-Thought Monitoring
• Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation
• Reasoning Models Struggle to Control their Chains of Thought
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
• DeepSeek-V3 Technical Report
• When Chain of Thought is Necessary, Language Models Struggle to Evade Monitors
• GLM-5: from Vibe Coding to Agentic Engineering
• A Rosetta Stone for AI Benchmarks
• Kimi K2: Open Agentic Intelligence
• Kimi K2.5: Visual Agentic Intelligence
• Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety
• Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems
• Hidden in Plain Text: Emergence & Mitigation of Steganographic Collusion in LLMs
• The Illusion of State in State-Space Models
• OpenAI GPT-5 System Card
• gpt-oss-120b & gpt-oss-20b Model Card
• Let's Think Dot by Dot: Hidden Computation in Transformer Language Models
• Preventing Language Models From Hiding Their Reasoning
• Stress Testing Deliberative Alignment for Anti-Scheming Training

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
• 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
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection