Do Latent-CoT Models Think Step-by-Step? A Mechanistic Study on Sequential Reasoning Tasks

2026-01-31

AI Summary

This study investigates whether Latent-CoT models, exemplified by CODI, genuinely perform implicit step-by-step reasoning. Employing interpretability techniques—including logit-lens decoding, linear probing, attention analysis, and activation patching—the work systematically examines how intermediate states are represented and propagated in polynomial iteration tasks. The analysis reveals, for the first time, that CODI constructs complete reasoning paths in short-hop tasks but shifts to relying on compressed shortcuts in long-hop settings, retaining only late-stage intermediate representations. This strategy proves highly fragile under distributional shifts or increased optimization difficulty, exposing a fundamental vulnerability in its reasoning process.

Technology Category

• Knowledge Representation and Reasoning: Computational Complexity of Reasoning
• Reasoning under Uncertainty: Other Foundations of Reasoning under Uncertainty
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Latent Chain-of-Thought (Latent-CoT) aims to enable step-by-step computation without emitting long rationales, yet its mechanisms remain unclear. We study CODI, a continuous-thought teacher-student distillation model, on strictly sequential polynomial-iteration tasks. Using logit-lens decoding, linear probes, attention analysis, and activation patching, we localize intermediate-state representations and trace their routing to the final readout. On two- and three-hop tasks, CODI forms the full set of bridge states that become decodable across latent-thought positions, while the final input follows a separate near-direct route; predictions arise via late fusion at the end-of-thought boundary. For longer hop lengths, CODI does not reliably execute a full latent rollout, instead exhibiting a partial latent reasoning path that concentrates on late intermediates and fuses them with the last input at the answer readout position. Ablations show that this partial pathway can collapse under regime shifts, including harder optimization. Overall, we delineate when CODI-style latent-CoT yields faithful iterative computation versus compressed or shortcut strategies, and highlight challenges in designing robust latent-CoT objectives for sequential reasoning.

Problem

• Latent Chain-of-Thought
• sequential reasoning
• iterative computation
• latent reasoning
• mechanistic study

Innovation

• Latent Chain-of-Thought
• mechanistic interpretability
• sequential reasoning
• intermediate-state representation
• distillation