arXiv:2608. 13607v1 Announce Type: new Abstract: Frontier LLMs are updated frequently and typically outperform their predecessors in aggregate.
Frontier LLMs are updated frequently and typically outperform their predecessors in aggregate. But aggregate gains say little about individual samples: an update can still cause sample-level regression, where a response correct under the old model becomes incorrect under the new one.
arXiv:2602. 20710v2 Announce Type: replace Abstract: Inspecting Chain-of-Thought reasoning is among the most common means of understanding why an LLM produced its output.
arXiv:2608. 04714v1 Announce Type: cross Abstract: Benchmark scores are reported as properties of a model, yet the inference framework used to produce them, such as HuggingFace, vLLM, or Ollama, are considered non-influential and their names and versions are almost never disclosed.
arXiv:2607. 17531v1 Announce Type: cross Abstract: Test-time collaboration, including self-consistency, best-of-N selection, critic models, and verifier pipelines, is often credited with broadly improving LLM reasoning, yet its gains are uneven and sometimes negative.
arXiv:2608. 15445v1 Announce Type: new Abstract: When a reward is correct on every training example yet consistent with more than one goal, a model can acquire an unintended one, a failure known as goal misgeneralization.
arXiv:2608. 08029v1 Announce Type: cross Abstract: Khatri et al.
arXiv:2606. 19549v1 Announce Type: new Abstract: Low-rank adaptation (LoRA) makes it cheap to train many domain- and task-specific language model adapters, but whether two adapters can be merged is usually discovered only after both have been fully trained and evaluated.
arXiv:2607. 28908v1 Announce Type: new Abstract: Reflection, the ability to revisit and revise prior reasoning, is central to how humans improve their answers.
arXiv:2607. 10139v1 Announce Type: cross Abstract: Selecting the correct answer from a pool of candidate reasoning chains is the engine of test-time scaling, yet the standard selectors each carry a cost: self-consistency inherits the errors of the single model it resamples, and trained reward models need labeled data and transfer poorly off-distribution.
arXiv:2510. 00492v3 Announce Type: replace Abstract: The reliability of large language models (LLMs) during test-time scaling is often assessed with \emph{external verifiers} or \emph{reward models} that distinguish correct reasoning from flawed logic.
arXiv:2607. 20129v1 Announce Type: new Abstract: Quantized small autoregressive reasoning models can enter long, repetitive, or unproductive trajectories, yet inference-time compute is usually allocated without observing how a trajectory develops.
arXiv:2608. 16210v1 Announce Type: new Abstract: Aggregate accuracy hides where models succeed and fail.