arXiv:2605. 19723v2 Announce Type: replace-cross Abstract: Mathematical reasoning is essential for problem-solving in education, science, and industry, serving as a crucial benchmark for evaluating artificial intelligence systems.
arXiv:2607. 20520v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly evaluated on mathematical problem solving, yet prior work often treats representationally equivalent formulations as interchangeable and conflates reasoning errors with interface failures.
arXiv:2604. 27960v2 Announce Type: replace Abstract: Recent large language models (LLMs) have achieved impressive reasoning milestones but continue to struggle with high computational costs, logical inconsistencies, and sharp performance degradation on high-complexity problems.
The paper introduces a neuro‑symbolic framework for scientific reasoning that separates symbolic validity and semantic groundedness. A deterministic symbolic verifier acts as a hard filter to guarantee syntactic and arithmetic correctness, while a Process Reward Model (PRM) is trained on verifier‑accepted steps to assess contextual grounding. The authors propose Counterfactual Symbolic Perturbation (CSP) to generate hard negative examples that pass the verifier but are logically flawed, enabling efficient PRM training and a verifier‑first constrained search at inference.
arXiv:2601. 22642v2 Announce Type: replace Abstract: Large Language Models (LLMs) show remarkable capabilities, yet their stochastic next-token prediction creates logical inconsistencies and reward hacking that formal symbolic systems avoid.
NL2AGBench is a benchmark that evaluates how well large language models can translate English geometry problems into the formal language required by AlphaGeometry’s theorem‑proving engine. The study tests ten state‑of‑the‑art LLMs, comparing executable translation accuracy, syntactic correctness, and error types, and finds a large gap between closed‑source and open‑source models. The authors also propose an error taxonomy and test mitigation strategies such as few‑shot prompting, fine‑tuning, and human‑guided hinting, which improve performance across model families.
The paper identifies a new failure mode in neurosymbolic systems called Verdict‑Preserving‑Unfaithfulness (VPU), where incorrect formal encodings can still pass solver checks. It introduces Generative Verification (GenV), a method that uses a language model to produce a continuous reference‑equivalence score without relying on explicit localization. Experiments show GenV+HN achieves high AUROC, generalizes to unseen translators, and improves downstream agent performance by 11.3 points.
arXiv:2606. 08728v1 Announce Type: new Abstract: Mathematical reasoning has long served as a stringent test of machine intelligence; over the past decade, it has moved from a niche problem within NLP to one of the most consequential AI frontiers.
The paper introduces Stratified Consistency Distillation, a fine‑tuning method to improve natural‑language to logical‑formula translations for neurosymbolic reasoning. It generates multiple candidate translations with a large LLM, clusters them by semantic equivalence, and selects pseudo‑labels using entropy‑based strategies—majority voting for low entropy, LLM-as‑Judge for medium entropy, and unification or abstention for high entropy. The selected pseudo‑labels are then used to fine‑tune a smaller model, yielding significant gains in Pass@K and a new Equivalent Logical Similarity metric.
arXiv:2607. 23019v1 Announce Type: new Abstract: Chain-of-thought (CoT) prompting enables large language models (LLMs) to tackle multi-step reasoning tasks, yet the generated intermediate steps are not guaranteed to be logically sound.
arXiv:2607. 04096v1 Announce Type: new Abstract: Current agentic workflows usually involve decomposing user requests into sequences of tool calls with correctly resolved parameters, the results of which are processed through reasoning traces in the language model's context window.
arXiv:2607. 29549v1 Announce Type: new Abstract: Large language models have demonstrated strong mathematical problem-solving capabilities, yet reliably verifying their candidate answers remains challenging.