There are two standard ways to spend more compute at test time: let a model reason longer, or sample more attempts and keep one. Both share a hidden limit: they are internal.
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: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.
arXiv:2606. 09046v1 Announce Type: new Abstract: Useful audits reveal not only how often a model fails, but also where its failures concentrate.
arXiv:2608. 06270v1 Announce Type: new Abstract: The "thinking-with-images" paradigm equips multimodal LLMs with active visual operations such as crop-and-zoom.
arXiv:2607. 28576v1 Announce Type: cross Abstract: Methods that make a language model plan, criticise and rewrite its own answer, reflect on mistakes, pick the best of several attempts, or debate with copies of itself nearly all make it generate far more text than a single chain of thought.
arXiv:2603. 28590v3 Announce Type: replace Abstract: Large language models (LLMs) can generate chains of thought (CoTs) that are not always causally responsible for their final outputs.
arXiv:2606. 15420v1 Announce Type: cross Abstract: A constitution tells a language model what to value, but little tells us whether it does.
arXiv:2608. 05670v1 Announce Type: new Abstract: A model's agreement across perturbed inputs is used both as a label-free reliability signal and as a self-training target, on the premise that agreement tracks correctness.
arXiv:2607. 25152v1 Announce Type: new Abstract: Long-running autonomous agents plan, act, and judge their own completion without human intervention.
arXiv:2607. 26117v1 Announce Type: cross Abstract: Self-repair - returning a failed program to the model together with its test output and asking for a correction - is a standard component of code agents, and is almost always evaluated against a baseline that does not retry at all.
arXiv:2607. 13305v1 Announce Type: cross Abstract: Benchmark accuracy in video large language models (LLMs) is often treated as evidence of visual understanding.
arXiv:2606. 28471v1 Announce Type: new Abstract: Model capability is the central variable in LLM pre-training, yet is never observed directly: data shapes it prospectively, while evaluation reveals it only retrospectively, compressing samples, prompts, decoding, and scoring rules into one noisy score.