Large reasoning models (LRMs) often improve math and coding performance, but their effect on instruction following is unclear. We study IFEval with Qwen3 models (1.
arXiv:2606. 01080v1 Announce Type: cross Abstract: Large language models often improve on difficult tasks by spending inference-time compute on a reasoning trace before producing the final answer.
arXiv:2608.29956v1 Announce Type: new Abstract: Large language models often answer complex reasoning questions without revealing intermediate steps, raising whether they reason latently or complete p...
arXiv:2607. 05184v1 Announce Type: new Abstract: Self-distillation is a promising recipe for self-improvement in language models.
arXiv:2603. 29025v3 Announce Type: replace-cross Abstract: Large language models fail when a salient surface cue conflicts with an unstated feasibility constraint.
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:2608. 09490v1 Announce Type: new Abstract: Task arithmetic treats fine-tuning displacements as composable directions in weight space, yet it remains unclear when parameter addition reflects predictable changes in model function.
arXiv:2609.37044v1 Announce Type: new Abstract: Explicit intermediate reasoning gives large language models (LLMs) a stronger problem-solving mode. We study learning from this think-mode advantage vi...
The paper investigates how privileged information—such as a teacher’s full solution or reasoning trace—affects on‑policy self‑distillation (OPSD) in language models. Using the AMPLE‑Math benchmark, the authors compare distillation with and without extra teacher views, finding that reference‑free distillation explains most gains for Qwen3‑1.7B, while additional references provide modest benefits, especially for polished solutions. The study also shows that the impact of privileged data depends on the student’s training regime and that altering token‑level supervision can leave student behavior largely unchanged.
arXiv:2510.01581v2 Announce Type: replace-cross Abstract: Recent thinking models are capable of solving complex reasoning tasks by scaling test-time compute, but this scaling should be allocated in l...
arXiv:2509. 14704v3 Announce Type: replace Abstract: Benchmark saturation and training-data contamination increasingly obscure whether reported gains in large language models (LLMs) reflect genuine advances in reasoning or familiarity with recurring patterns in benchmark problems.
The paper introduces the Grounded Integration Measure (GIM), a benchmark of 820 expert‑authored problems designed to test models on tasks that integrate multiple cognitive operations such as constraint satisfaction, state tracking, epistemic vigilance, and audience calibration. GIM emphasizes realistic, broadly accessible knowledge rather than specialized expertise, and uses a judge‑aware 2‑parameter logistic IRT model to produce robust ability estimates across 53 model‑thinking‑level configurations. The authors provide a comprehensive leaderboard of 22 models and 47 test configurations, and conduct an extensive study on how test‑time compute affects model capability, finding that configuration choices like thinking budget and quantization can be as influential as model selection itself. whyItMatters":"By focusing on integration of multiple cognitive domains, GIM offers a more realistic assessment of model reasoning capabilities than benchmarks that either overemphasize memorization or abstract reasoning alone."
arXiv:2609.00768v2 Announce Type: replace Abstract: Self-play supports the self-evolution of language models, but solver performance can plateau or decline across rounds without guidance. Existing un...