arXiv AI July 15, 2026 By Dongyue Li, Zhenshuo Zhang, Minxuan Duan, Edgar Dobriban, Hongyang R. Zhang

Efficiently Learning Branching Networks for Multitask Algorithmic Reasoning

arXiv:2512. 01113v2 Announce Type: replace-cross Abstract: Algorithmic reasoning -- the ability to perform step-by-step logical inference -- is a synthetic benchmark for evaluating multi-step reasoning abilities, designed for graph neural networks and also for transformer models.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Aug 6

Topology-Aware Reasoning over Incomplete Knowledge Graph with Graph-Based Soft Prompting

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

llms rag nlp benchmarks safety

arXiv AI

Aug 14

Unified Multi-Dimensional Benchmark for Complex Graph Reasoning in Large Language Models

arXiv:2608. 12391v1 Announce Type: cross Abstract: Graph reasoning provides a promising testbed for evaluating the reasoning ability of large language models (LLMs), as graph instances can be programmatically generated, structurally controlled, and naturally scaled to long-input settings.

By Fali Wang, Ali Al-Lawati, Iliyas Bektas, Jinxuan Fang, Alek Melenski, Tianxiang Zhao, Yao Ma, Suhang Wang

llms rag fine-tuning benchmarks

arXiv AI

Jul 28

How Transformers Learn to Plan via Multi-Token Prediction

arXiv:2604. 11912v2 Announce Type: replace-cross Abstract: While next-token prediction (NTP) has been the standard objective for training language models, it often struggles to capture global structure in reasoning tasks.

By Jianhao Huang, Zhanpeng Zhou, Renqiu Xia, Baharan Mirzasoleiman, Weijie Su, Wei Huang

llms benchmarks safety

arXiv AI

Aug 25

Which Algorithms Can Graph Neural Networks Learn?

arXiv:2602.13106v2 Announce Type: replace-cross Abstract: In recent years, there has been growing interest in understanding neural architectures' ability to learn to execute discrete algorithms, a li...

By Solveig Wittig, Antonis Vasileiou, Robert R. Nerem, Timo Stoll, Floris Geerts, Yusu Wang, Christopher Morris

efficiency

arXiv Machine Learning

Aug 3

Mining Verdict Boundaries for Neural Network Verification

arXiv:2607. 28954v1 Announce Type: new Abstract: Branch and Bound (BaB) aims to achieve complete verification of neural networks by adaptively partitioning the problem and applying off-the-shelf verifiers to subproblems.

By Jiawei Ren, Guanqin Zhang, Zhenya Zhang, Yulei Sui

benchmarks

arXiv Computation and Language

Sep 16

Optimal Model Activation Policies for Inference Networks of Large Language Models

arXiv:2609.15992v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have rendered them necessary for Natural Language Processing (NLP) tasks, and their high inference cost...

By Foivos Charalampakos, Md Ibrahim Ibne Alam, Iordanis Koutsopoulos, Koushik Kar

llms nlp

One email a morning, machine-written

Related stories

Topology-Aware Reasoning over Incomplete Knowledge Graph with Graph-Based Soft Prompting

Unified Multi-Dimensional Benchmark for Complex Graph Reasoning in Large Language Models

How Transformers Learn to Plan via Multi-Token Prediction

Which Algorithms Can Graph Neural Networks Learn?

Mining Verdict Boundaries for Neural Network Verification

Optimal Model Activation Policies for Inference Networks of Large Language Models