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.
UpgradeBench is a decision‑centric longitudinal benchmark that evaluates how fine‑tuned language‑model specialists should be handled when new base‑model releases occur. It covers four consecutive Qwen releases, a continuation checkpoint, six tasks, two model sizes, and OLMo checkpoints with known training lineage, and examines whether retraining, adapter transfer, or other recovery strategies improve specialist performance. The benchmark reveals that upgrade gains vary by task and release interval, that direct adapter copying is sensitive to pretraining distance, and that teacher relabeling can recover specialists without new annotations. "whyItMatters":"The study provides actionable insights into the cost‑effective management of specialist models across model releases, showing how to balance retraining effort with performance gains."
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.
The paper introduces RAISE, a diagnostic framework that tests whether a costly large language model (LLM) signal provides enough pre-call information to justify selective use. It identifies the failure mode of acquisition collapse, where an LLM appears useful overall but lacks actionable evidence for individual decisions. The authors demonstrate RAISE with Structured Hypothesis Embeddings (SHE) and evaluate it across multiple study designs, showing that predictable incremental benefit, rather than average lift, indicates recoverable selective value.
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:2610.08514v1 Announce Type: new Abstract: Execution feedback lets coding agents revise programs and learn from their own corrections. A correction's learning weight should reflect both the tran...
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.