arXiv:2603.00578v2 Announce Type: replace-cross Abstract: Long chain-of-thought~(CoT) reasoning improves the problem-solving capability of large reasoning models~(LRMs), but often incurs substantial...
arXiv:2605. 15454v2 Announce Type: replace-cross Abstract: Reasoning-trained language models often spend more tokens on harder problems, but longer chains of thought do not show whether a model is merely computing for more steps or following a different internal trajectory.
arXiv:2604. 06628v2 Announce Type: replace Abstract: A prevailing narrative in LLM post-training holds that supervised finetuning (SFT) memorizes while reinforcement learning (RL) generalizes.
arXiv:2610. 02191v1 Announce Type: new Abstract: While Large Language Models (LLMs) have demonstrated striking capabilities on frontier mathematical problems, it remains unclear whether they possess the structural mathematical understanding underlying their solutions.
arXiv:2510. 18428v4 Announce Type: replace Abstract: Optimization modeling underlies critical decision-making across industries, yet remains difficult to automate: natural-language problem descriptions must be translated into precise mathematical formulations and executable solver code.
arXiv:2603.18614v2 Announce Type: replace Abstract: Tool-augmented large language models (LLMs) must tightly couple multi-step reasoning with external actions, yet existing benchmarks often confound...
LiveMathematicianBench is a dynamic multiple‑choice benchmark for research‑level mathematical reasoning, built from recent arXiv papers published after model training cutoffs. It introduces a thirteen‑category logical taxonomy of theorem types and uses a proof‑sketch‑guided distractor pipeline to create plausible but invalid answer choices, enhancing sensitivity to genuine reasoning. Evaluation shows current large language models perform poorly, with the best model scoring 43.5% overall and only 17.6% under substitution‑resistant conditions, indicating the benchmark’s difficulty and realism.
The paper proposes a unified framework for test‑time reasoning methods, framing them as recursion operators—GROW, PRUNE, and BRANCH—applied to an agent’s reasoning trace. Experiments across five benchmarks and three frontier models show that BRANCH, which samples and selects among multiple reasoning paths, consistently outperforms the other operators and a single‑pass chain‑of‑thought baseline, improving accuracy by an average of 5.98 percentage points. The study also highlights the importance of paired evaluation and careful handling of scoring‑pipeline failures, as these factors can significantly alter comparative outcomes.
arXiv:2604.27251v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) acquire reasoning capabilities through shared inference patterns in pre-training data, which are further elicite...
arXiv:2609.16055v1 Announce Type: cross Abstract: Test-time compute has emerged as a major approach to improving the capabilities of Large Language Models (LLMs). However, existing test-time reasonin...
arXiv:2609.24066v1 Announce Type: new Abstract: Best-of-$N$ is a widely used inference strategy for complex reasoning, whose effectiveness depends on whether sampled candidates can cover diverse and...
arXiv:2608.16831v2 Announce Type: replace Abstract: Pretrained large language models offer a practical foundation for learning useful behavior from few task-specific examples. We argue that current p...