The Ends Justify the Thoughts: RL-Induced Motivated Reasoning Fools CoT Monitors

arXiv:2510.17057 · cs.LG, cs.AI · Submitted 2025-10-20 · Read on arXiv

cs.LG, cs.AI

Submitted: 2025-10-20

Updated: 2026-10-18

Terminology

• Chain-of-Thought (CoT) — 1× in this paper · explained in 5 episodes
• Reward Hacking — 1× in this paper · explained in 11 episodes
• Trace — 1× in this paper · explained in 2 episodes

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