arXiv:2604. 06501v2 Announce Type: replace Abstract: Analogical reasoning is a hallmark of human intelligence, enabling us to solve new problems by transferring knowledge from one situation to another.
arXiv:2609.25438v1 Announce Type: new Abstract: Diverse pretraining has been shown to be an effective method for learning reusable, domain-aware representations that provide a starting point for fine...
arXiv:2604. 07822v2 Announce Type: replace-cross Abstract: We study implicit reasoning, i.
The paper introduces graph metanetworks for transformer-based language models, addressing the challenge that different weight configurations can implement the same function due to a rich symmetry group. It formalizes a weight‑space symmetry group for complete decoder‑only language models and presents a graph construction invariant to these symmetries. The authors also create two new transformer‑population datasets with tasks like training‑corpus prediction and fine‑tuning detection, where their method outperforms existing baselines.
arXiv:2505. 20161v2 Announce Type: replace-cross Abstract: Effective generalization in language models depends critically on the diversity of their training data.
arXiv:2608. 08113v1 Announce Type: new Abstract: Chain-of-Thought (CoT) prompting has become the dominant paradigm for eliciting reasoning in Large Language Models (LLMs), yet it creates substantial computational overhead by forcing models to externalize intermediate reasoning steps as discrete tokens.
arXiv:2510. 25013v2 Announce Type: replace-cross Abstract: Mechanistic interpretability aims to reverse-engineer large language models (LLMs) into human-understandable computational circuits.
arXiv:2606. 19317v1 Announce Type: cross Abstract: A longstanding goal of research on interpretable deep learning is to replace opaque neural computations with human-meaningful symbolic descriptions.
The paper presents a taxonomy of 28 cognitive elements derived from cognitive science to analyze reasoning in large language models (LLMs). Using a fine‑grained evaluation framework, the authors compare 192,000 model traces with 1,346 human think‑aloud traces, finding that while models deploy similar cognitive elements, they differ in usage patterns. The study introduces test‑time reasoning guidance that improves model accuracy on ill‑structured problems by 9.7 percentage points and highlights a research gap in self‑awareness, advocating for a shared vocabulary to diagnose failures and guide robust model development.
ConceptARC at Scale introduces a generator that produces thousands of ARC-style tasks focused on specific spatial and semantic concepts, expanding the original benchmark by tenfold. The new dataset, ConceptARC-100, contains 1,600 manually reviewed tasks across 16 concepts, each with 100 tasks. Evaluation of large reasoning models on this dataset reveals that they reliably solve certain concepts, struggle with others, and develop internal representations that cluster by transformation operations such as recoloring, removal, or translation.
arXiv:2607. 25915v1 Announce Type: new Abstract: Complex structured reasoning tasks often require additional computation, yet current language models obtain it mainly by increasing parameter scale or by serializing intermediate steps as chain-of-thought (CoT) tokens.
Thought‑Like‑Pro is a learning framework that enhances large language models’ reasoning by combining imitation learning with a Prolog logic engine. The approach imitates chain‑of‑thought processes verified by symbolic reasoning, allowing models to formulate rules from instructions and convert Prolog‑derived reasoning trajectories into natural language. Experiments show significant reasoning improvements and robust generalization with only a marginal performance drop on distributional extrapolation tasks.
arXiv:2505.22635v2 Announce Type: replace-cross Abstract: A common approach for teaching large language models (LLMs) to reason is to train on chain-of-thought (CoT) traces of in-distribution reasoni...