VISPATH is a visual‑intent‑guided path reasoning framework designed for multimodal knowledge graph question answering (MM‑KGQA). It first identifies a reliable starting entity by fusing multimodal grounding with graph‑structural cues, then iteratively discovers and refines reasoning paths using hop‑specific multimodal intent and a reasoning‑chain pruning step. The framework is evaluated on the newly introduced VISPATH‑Bench, which tests two‑to‑four‑hop reasoning, and demonstrates consistent improvements over strong baselines, even surpassing GPT‑5.4 when using GPT‑4o as the backbone.
By Jinke Wu, Zhengpin Li, Mengzhe Jia, Yang Li, Wentao Zhang
arXiv:2609.14528v1 Announce Type: cross
Abstract: Multi-Hop Knowledge Graph Question Answering (KGQA) tasks require models to assemble relational evidence along paths in a KG to answer natural-langua...
By Eduin E. Hernandez, Luis F. Garcia, Nurassyl Askar, Sergio A. Diaz, Stefano Rini
arXiv:2603.16654v3 Announce Type: replace-cross
Abstract: Evaluating the reasoning abilities of large language models (LLMs) solely from final answers can obscure failures in intermediate steps, espe...
By Xiaojie Gu, Sherry T. Tong, Aosong Feng, Sophia Simeng Han, Jinghui Lu, Yingjian Chen, Yusuke Iwasawa, Yutaka Matsuo, Chanjun Park, Rex Ying, Irene Li
arXiv:2609.39346v1 Announce Type: new
Abstract: Large language models (LLMs) offer strong reasoning capabilities but are often costly to access through commercial APIs, while small language models (S...
By Bohan Zhang (Southeast University), Linan Yue (Southeast University), Weibo Gao (Hong Kong Polytechnic University), Pengyu Chen (Southeast University), Hong Guo (Southeast University), Yanqi Hao (ZTE Corporation)
arXiv:2604. 12503v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have shown remarkable capabilities across various tasks but remain prone to hallucinations in knowledge-intensive scenarios.
By Shuai Wang, Xixi Wang, Yinan Yu
arXiv:2606. 03705v1 Announce Type: new Abstract: Knowledge Graphs (KGs) are widely used to mitigate the limitations of Large Language Models (LLMs), such as outdated knowledge and hallucinations.
By Weiwei Ding, Zixuan Li, Long Bai, Zhuo Chen, Kun Su, Fei Wang, Xiaolong Jin, Jin Zhang, Jiafeng Guo, Xueqi Cheng
arXiv:2609.39786v1 Announce Type: new
Abstract: Large language models (LLMs) are increasingly combined with knowledge graphs (KGs) to ground reasoning in structured evidence. However, most LLM-based...
By Ola El Khatib, Djellel Difallah
arXiv:2602. 16902v4 Announce Type: replace Abstract: We introduce LLM-Wikirace, a benchmark for evaluating planning, reasoning, and world knowledge in large language models (LLMs).
By Juliusz Ziomek, William Bankes, Lorenz Wolf, Shyam Sundhar Ramesh, Xiaohang Tang, Ilija Bogunovic
DynSTEER is a dynamic stage‑wise trajectory evaluation framework designed for large language model agents performing long‑horizon tasks. It segments rollouts into stages anchored by key actions, uses a path‑tolerant milestone graph to accommodate diverse valid strategies, and adaptively routes queries to multi‑tier judges while halting unrecoverable executions early. Experiments show it improves evaluation discriminability by 85.2% over native methods, separates all model pairs with statistical significance, and saves 34.51% of execution steps on failed rollouts.
By Zhichao Shi, Wenjie Zhang, Xuhui Jiang, Xiaojun Wu, Cehao Yang, Chengjin Xu, Jian Guo, Yuanzhuo Wang
TRACES (Tagging Reasoning Steps for Adaptive Cost‑Efficient Early‑Stopping) is a lightweight framework that tags reasoning steps of large‑language models in real time, enabling adaptive, cost‑efficient early stopping during inference. By monitoring the types of steps generated, the method identifies when models shift their reasoning after arriving at a correct answer, allowing for interpretable stopping criteria. Experiments on mathematical reasoning benchmarks (MATH500, GSM8K, AIME) and knowledge benchmarks (MMLU, GPQA) show token reductions of 20–50% while preserving accuracy, with more conservative thresholds needed for harder tasks such as BeyondAIME and IMO AnswerBench.
By Yannis Belkhiter, Seshu Tirupathi, Giulio Zizzo, John D. Kelleher
The paper proposes PAIR, a method that treats reasoning paths of large language models as phase‑structured trajectories within each question. By sampling multiple trajectories per question, aligning them to shared relative phases, and comparing successful versus unsuccessful paths only within the same phase, PAIR isolates path‑quality signals from question‑level variation. Experiments show that standard correctness probes lose predictive power under this within‑question evaluation, while PAIR improves trajectory ranking, Best‑of‑N selection, and enables phase‑wise steering of generation outcomes.
By Zhenghao He, Guangzhi Xiong, Sanchit Sinha, Bohan Liu, Wenqian Ye, Aidong Zhang
arXiv:2608. 07954v1 Announce Type: new Abstract: Large language models can answer knowledge-intensive questions more reliably when they are grounded with knowledge graphs, but systems such as Think-on-Graph and Reasoning-on-Graph repeatedly query the same graph neighborhoods across different questions.
By Uros Stanic, Changcheng Yuan, Sabuj Laskar, Ariful Azad