LLM Reasoning Is Latent, Not the Chain of Thought

arXiv:2604.15726v1 Announce Type: new Abstract: This position paper argues that large language model (LLM) reasoning should be studied as latent-state trajectory formation rather than as faithful surface chain-of-thought (CoT). This matters because claims about faithfulness, interpretability, reasoning benchmarks, and inference-time intervention all depend on what the field takes the primary object of reasoning to be. We ask what that object should be once three often-confounded factors are separated and formalize three competing hypotheses: H1, reasoning is primarily mediated by latent-state trajectories; H2, reasoning is primarily mediated by explicit surface CoT; and H0, most apparent reasoning gains are better explained by generic serial compute than by any privileged representational object. Reorganizing recent empirical, mechanistic, and survey work under this framework, and adding compute-audited worked exemplars that factorize surface traces, latent interventions, and matched budget expansions, we find that current evidence most strongly supports H1 as a default working hypothesis rather than as a task-independent verdict. We therefore make two recommendations: the field should treat latent-state dynamics as the default object of study for LLM reasoning, and it should evaluate reasoning with designs that explicitly disentangle surface traces, latent states, and serial compute.

Related

• When More Thinking Hurts: Overthinking in LLM Test-Time Compute Scaling
• On the Step Length Confounding in LLM Reasoning Data Selection
• Revisiting the Capacity Gap in Chain-of-Thought Distillation from a Practical Perspective
• Efficient Process Reward Modeling via Contrastive Mutual Information
• STU-PID: Steering Token Usage via PID Controller for Efficient Large Language Model Reasoning

Source: arXiv cs.AI | 2026-04-20