Ceiling of a Task: When Can a Transformer Succeed Without Its Chain of Thought?
Analyzes tasks for which a fixed-depth transformer needs an informative chain of thought to exceed a task-specific accuracy limit. Combines circuit-based results with experiments that replace, erase, or shuffle reasoning tokens, including comparisons with filler tokens.
First public: · Added to this list: October 18, 2026
Cite this paper
ArXiv preprint
arXiv:2609.33134 · Initial submission: 2026-09-27
A published-version citation has not been verified for this entry. This does not mean the paper is unpublished.
Choose the version you used. The arXiv link may serve a revision; check the original paper for the exact result, assumptions and limitations you cite.
Explore this approach
Analysis and evaluation — Measure how well these methods work, investigate what their internal computation does, and identify where they fail. This includes experiments, studies of model internals, and mathematical results.
Thinking tokens — Give a model extra tokens for computation, such as pauses, filler symbols, or learned planning tokens. These tokens need not spell out the solution.
Read or reuse this entry
Plain-text Markdown · JSON record · Find in the full list
Our summary and categories are a reading aid, not the authors’ abstract. Use the original paper for research claims. Suggest a correction.