arXiv:2608. 02089v1 Announce Type: new Abstract: Large language models often show users a final response and a short reasoning summary while the full reasoning trace stays hidden.
arXiv:2608. 03291v1 Announce Type: cross Abstract: Chain-of-thought (CoT) reasoning improves large language model (LLM) performance while also providing an observable interface to the model's reasoning process.
arXiv:2608. 17638v1 Announce Type: new Abstract: What a reasoning model writes is only a partial record of the process that produces it.
arXiv:2608. 03401v1 Announce Type: cross Abstract: Large language models often reason at length before answering, increasing cost and latency.
arXiv:2607. 16451v1 Announce Type: cross Abstract: Chat models sometimes commit to an answer and then produce reasoning that justifies it rather than deriving it -- even when the answer contradicts a task premise.
arXiv:2608. 13329v1 Announce Type: new Abstract: A model that behaves differently when it senses it is being tested would undermine the evaluations we rely on, so recent work has sought to read that sense directly from a model's activations.
What a reasoning model writes is only a partial record of the process that produces it. We introduce a two-level internal readout for mixture-of-experts reasoning.
arXiv:2607. 16997v1 Announce Type: new Abstract: Mathematicians distinguish proofs that explain, simplify, or introduce a nonstandard route, but these judgments are difficult to operationalize.
arXiv:2608. 15022v1 Announce Type: new Abstract: Language models hold latent quantities in a form they can report on, and more of a quantity is present in that form when the task requires reusing it flexibly.
arXiv:2606. 09046v1 Announce Type: new Abstract: Useful audits reveal not only how often a model fails, but also where its failures concentrate.
arXiv:2607. 11598v1 Announce Type: new Abstract: There are two standard ways to spend more compute at test time: let a model reason longer, or sample more attempts and keep one.
arXiv:2607. 04572v1 Announce Type: new Abstract: Large language model (LLM) tutors often produce fluent step-by-step explanations, but a correct and pedagogically formatted response does not guarantee that the answer was derived from the student-facing problem.
arXiv:2604. 16706v2 Announce Type: replace Abstract: Automated evaluation of tool-using large language model (LLM) agents is widely assumed to be reliable, yet this assumption is rarely validated against human annotation.