Harvard-linked study finds reasoning models get stuck on their first few words

A paper posted to arXiv on October 29, 2026 as arXiv:2610.40939, "The First Few Tokens Matter: Understanding Chain-of-Thought Controllability," by Harvard student Hugh Van Deventer and colleagues at Harvard and the Cambridge Boston Alignment Initiative, found that reasoning models such as OpenAI's o1 series suffer "entropy collapse" — locking onto a small set of default opening tokens right after their thinking tag — and that banning those default openers and adding in-context examples raised instruction compliance by 34 to 41 percentage points across the tested models. The gains held for addition and style controllability but were variable for suppression, the ability to keep specified information out of reasoning, which the authors argue should be evaluated separately. The interventions are low-cost, inference-time adjustments rather than retraining.

Harvard-linked study finds reasoning models get stuck on their first few words Banning default opening tokens and adding an example lifted compliance by 34 to 41 percentage points across tested models AI reasoning models are supposed to think step by step. A new paper suggests they mostly start those steps the same way, and that habit makes them harder to steer. Researchers found that two cheap tricks, banning the usual opening words and adding an example, improved how well reasoning models followed instructions by 34 to 41 percentage points . For a field that spends heavily on bigger models, that is a large gain from tweaking a few words at the start. What the researchers found The paper is titled “The First Few Tokens Matter: Understanding Chain-of-Thought Controllability.” It was posted to arXiv on October 29, 2026, as arXiv:2610.40939, and runs 20 pages with 15 figures. The authors include Harvard student Hugh Van Deventer and colleagues. They are affiliated with Harvard and the Cambridge Boston Alignment Initiative. Their focus is chain-of-thought, or CoT. That is the visible “scratchpad” reasoning a model writes before giving a final answer. The study pays particular attention to large language models such as the OpenAI https://cryptobriefing.com/markets/openai/ o1 series. The core finding is something the authors call entropy collapse . It shows up in the first tokens a model produces right after its opening thinking tag. A quick translation helps. A token is a chunk of text, roughly a word or part of one. Entropy, in this context, measures how varied the model’s choices are. High entropy means many plausible next words. Low entropy means the model is effectively locked onto a few. So entropy collapse means that at the very start of its reasoning, the model keeps reaching for the same small set of familiar opening tokens. That narrowness matters because the opening shapes everything after it. If a user asks the model to reason in a certain style or include certain information, the model’s default opener can pull it back toward its usual script. AI, tech, and the markets they move—in one daily briefing. Daily. Free. Join 34,000+ readers across crypto, finance, and policy. Two small fixes, one big jump The researchers tested interventions aimed squarely at those first few tokens. Two stood out. The first is prefilling . Here, the user supplies the opening of the model’s reasoning, even as little as a single token, instead of letting the model choose. The second combines two moves. The researchers banned the common default opening tokens, then added in-context examples showing what the desired reasoning should look like. Together, these strategies raised compliance by 34 to 41 percentage points across the models tested. Compliance here means how often the model’s reasoning actually followed the instructions it was given. The gains were not uniform across every type of control, though. The study separates controllability into different capabilities. Addition and style controllability covers cases where a model is asked to add information or change how its reasoning is expressed. These saw the clear improvement. Suppression is different. It covers asking a model to avoid specific information in its reasoning. Here, the effects of the interventions were variable. That split is telling. The authors suggest these distinct capabilities may need different evaluation approaches rather than being lumped into one score. What this means The most practical takeaway is cost. The interventions described are low-cost adjustments made at inference time, meaning when the model is being used, not when it is being trained. The uneven suppression results are the part worth watching. Many oversight scenarios depend on a model avoiding certain content, not just adding it. If suppression does not respond as consistently to these tricks, then measuring it separately, as the authors suggest, becomes important. Treating all controllability as one number could make a model look more steerable than it really is in the cases that matter most. Disclosure: This article was edited by Diego Almada Lopez. For more information on how we create and review content, see our Editorial Policy https://cryptobriefing.com/editorial-policy/ . More in AI See all https://cryptobriefing.com/artificial-intelligence/