Research radar

arXiv preprints, filtered for developer impact.

Concise summaries of new AI papers, ranked for how likely they are to change how production systems are built. arXiv collection remains rate-limited.

Papers tracked

2,287

matching records

Shown

current page

Top radar

http://arxiv.org/abs/2608.24846v1

Code links

on this page

Paper	Authors	arXiv ID	Categories	Published	Code	Radar	Summary
FedV-KGQA: Multi-Hop Question Answering over Vertically Partitioned Knowledge Graphs	Md Saikat Islam Khan Bappy, Oshani Seneviratne	http://arxiv.org/abs/2608.24846v1	cs.AI	Aug 25, 2026	None	RDR77	Real-world data for knowledge graph question answering is often distributed across different...
A Dual-Dimensional LLM Framework for Automated Item Incidental Content Similarity Analysis in Large-Scale Assessments	Jing Huang, Jihong Zhang, Hua-Hua Chang	http://arxiv.org/abs/2608.24825v1	cs.AI	Aug 25, 2026	None	RDR73	The rapid expansion of large-scale assessments and the growing adoption of automatic item gen...
Structurally-bounded Agentic Graph Exploration for Evidence-Grounded Scholarly DeepSearch	Rima Hazra, Sayan Layek, Somnath Banerjee	http://arxiv.org/abs/2608.24809v1	cs.CL, cs.IR	Aug 25, 2026	None	RDR74	We present Crase, a bounded and inspectable alternative to deep research agents for scholarly...
A Visual Dependence-Aware Framework for Multimodal Unsupervised Continual Post-Training	Kaichen Li, Zhilin Zhu, Jianhao Huang	http://arxiv.org/abs/2608.26095v1	cs.CV, cs.AI	Aug 26, 2026	None	RDR66	In this paper, we explore a novel task of Multimodal Unsupervised Continual Post-Training (MU...
Group-Shared Low-Rank Approximation for Mobile-Efficient Pointwise Convolutions in Large-Kernel CNNs	Hao Luo, Yiting Yang, Wenyi Zhao	http://arxiv.org/abs/2608.26069v1	cs.LG	Aug 26, 2026	None	RDR65	Large-kernel Convolutional Neural Networks (CNNs) deliver remarkable performance in vision ta...
The Value of Human Expertise	Bradley Sturt	http://arxiv.org/abs/2608.26051v1	math.OC, cs.AI	Aug 26, 2026	None	RDR82	We consider optimization applications with unknown parameters where the decision maker believ...
Improving Cross-Problem Vehicle Routing with Locally Augmented Preferences and Representation Disentanglement	Arthur Corrêa, Paulo Nascimento, Samuel Moniz	http://arxiv.org/abs/2608.24859v1	cs.LG	Aug 25, 2026	None	RDR76	Multi-task vehicle routing problem (VRP) solvers seek to handle multiple VRP variants within...
Bellman Calibration for Marginalized Importance Weighting in Offline Reinforcement Learning	Lars van der Laan, Nathan Kallus	http://arxiv.org/abs/2608.24858v1	cs.LG, stat.ML	Aug 25, 2026	None	RDR78	Marginalized importance weighting evaluates a target policy by reweighting offline state-acti...
Reading Is Not Using: Retrieval, Judgment, and the Design of AI Financial Research Workflows	Miao Liu, Zhizhe Liu	http://arxiv.org/abs/2608.24842v1	cs.CL, cs.AI	Aug 25, 2026	None	RDR78	Large language models (LLMs) are increasingly deployed as AI analysts to process financial di...
Constrained Entity Selection under Partial Knowledge for LLM-Based Knowledge Graph QA	Emanuel Kitzelmann	http://arxiv.org/abs/2608.24824v1	cs.AI	Aug 25, 2026	None	RDR73	Large language models are increasingly used for knowledge graph question answering (KGQA), bu...