arXiv:2606. 05983v1 Announce Type: new Abstract: Generative AI makes answers easy and understanding hard, and uncritical use invites cognitive offloading.
arXiv:2606. 06546v1 Announce Type: new Abstract: Evaluating large language models (LLMs) for education requires measuring how models teach, not only what they know.
arXiv:2608. 04794v1 Announce Type: new Abstract: Self-distillation (SD) has emerged as a compute-efficient alternative to reinforcement learning with verifiable rewards: a self-teacher, conditioned on privileged information (PI) about the answer such as a reference solution, supplies dense per-token supervision to a student that never sees it.
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:2607. 08255v1 Announce Type: new Abstract: Large language models increasingly serve as teachers generating training data for smaller students.
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.
arXiv:2606. 12422v1 Announce Type: cross Abstract: The integration of large language models (LLMs) into educational assessment represents a transformative shift in classroom grading practices.
arXiv:2609.26094v1 Announce Type: new Abstract: Multi-step causal reasoning requires chaining inferences where each step constrains the next. An early error propagates silently, and a correct answer...
arXiv:2606. 29971v1 Announce Type: new Abstract: A growing body of work suggests that the reasoning capabilities of large language models are largely latent in their base form, with post-training primarily amplifying rather than introducing them.
arXiv:2603. 00077v3 Announce Type: replace-cross Abstract: Rubric-based LLM judges have become indispensable for evaluating and optimizing systems on non-verifiable tasks, where success cannot be reduced to exact programmatic checks.
PotARCin expands the ARC benchmark by evaluating abstract reasoning across five dimensions—Definition, Classification, Constrained Generation, Editing, and Inversion—using programmatic generation of new task instances. The study shows a 25‑52 percentage‑point performance gap between standard ARC evaluation and PotARCin, and reveals that multi‑dimensional assessment can reorder models that appear equivalent under single‑metric accuracy. Additionally, a new held‑out set, P‑ARC, demonstrates low model accuracy (1‑8%) across all dimensions, highlighting the need for more comprehensive tests of abstract reasoning.
LLM-as-judge is essential for evaluating open-ended text and steering post-training, yet improving the judge itself typically relies on expensive annotations, reward models, or distillation from stron...
The paper introduces a recursive self-improvement framework for language models that replaces an external teacher with a frozen copy of the student, enabling dynamic co-evolution (DCE) and self-refined concise learning (SRCL). DCE allows the privileged teacher to evolve alongside the student, while SRCL trains on shorter, verified rewrites to reduce verbosity. Experiments show that the combined DCE+SRCL approach outperforms traditional on‑policy self‑distillation across multiple model sizes and math benchmarks, achieving significant accuracy gains and shorter outputs.