arXiv:2608.22753v1 Announce Type: new
Abstract: Large language models (LLMs) excel at text understanding and generation, yet still struggle to reliably understand and apply externally provided proced...
By Bohan Yu, Pengfei Cao, Chen Han, Chenxi Zhou, Zhiheng Zhang, Zhiyang Xie, Wenhao Teng, Xiangwen Liao, Jun Zhao, Kang Liu
arXiv:2508. 10971v2 Announce Type: replace-cross Abstract: Knowledge graphs (KGs) can be enhanced through rule mining; however, the resulting logical rules are often difficult for humans to interpret due to their inherent complexity and the idiosyncratic labeling conventions of individual KGs.
By Nasim Shirvani-Mahdavi, Chengkai Li
arXiv:2606. 03269v1 Announce Type: new Abstract: Visual Question Answering (VQA) is the task of answering questions about images, requiring the integration of multimodal input and reasoning.
By Thomas Eiter, Nelson Higuera Ruiz, Johannes Oetsch
The paper introduces Tasks over Application Manuals (TAM), a benchmark designed to test long‑horizon procedural reasoning in large language models. TAM uses real‑world tasks from ICD‑10‑CM clinical coding and U.S. federal sentencing, requiring models to follow extensive, rule‑based manuals and perform interdependent steps to produce exact answers. Experiments with GPT‑5 and various prompting strategies show very low exact‑match accuracy—1% for coding and 15.5% for sentencing—highlighting a gap between current benchmarks and the ability to reliably follow complex procedures.
By Utkarsh Soni, Syed Shariyar Murtaza, Yifan Nie, Sachin Chandrasekhar, Eugene Wen
arXiv:2606. 23238v2 Announce Type: replace Abstract: Logical reasoning is essential for reliable AI, yet existing benchmarks are largely first-order-logic-centric, focusing on object-level deduction over fixed predicates.
By Yucheng Wu, Jundong Xu, Mingzhen Ju, Yue Yu, Chenpeng Wang, Haoxuan Li, Liangming Pan
RGDT-Bench is a new benchmark that evaluates large language models on Rule‑Governed Decision Tasks, where models must apply external rules to facts, justify decisions, and provide checkable justifications. The benchmark offers 202.1K condition‑level supervision slots across four task tracks and eight task‑probe combinations, and it labels warrant completeness through label‑blind extraction and deterministic checks. Evaluation shows that among correct responses, 40.2% of warrants are incomplete, and existing evaluators struggle to detect this, prompting the authors to train a reward model that improves AUROC to 69.24% and outperforms outcome‑supervised baselines.