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

180

1 arXiv sources

Top radar

http://arxiv.org/abs/2605.30352v1

Published 24h

by paper date

Rate limit

1/3s

arXiv policy

Paper	Authors	arXiv ID	Categories	Published	Code	Radar	Summary
EdgeFlow: Edge-Map Augmented VLM-Based Flowchart Processing for Industrial Requirements Engineering	Zhifei Dou, Shabnam Hassani, Ou Wei	http://arxiv.org/abs/2605.27332v1	cs.SE, cs.AI	May 26, 2026	None	RDR86	Flowcharts are widely used in industrial requirements, but usually remain embedded as static...
Chartographer: Counterfactual Chart Generation for Evaluating Vision-Language Models	Yifan Jiang, Dae Yon Hwang, Jesse C. Cresswell	http://arxiv.org/abs/2605.27311v1	cs.CL, cs.CV	May 26, 2026	None	RDR86	Chart question-answering (QA) benchmarks aim to pose questions that require visual reasoning...
From Model Scaling to System Scaling: Scaling the Harness in Agentic AI	Shangding Gu	http://arxiv.org/abs/2605.26112v1	cs.AI, cs.LG	May 25, 2026	Detected	RDR86	This paper studies the next major bottleneck in agentic AI as system scaling, not only model...
Prism: A Plug-in Reproducible Infrastructure for Scalable Multimodal Continual Instruction Tuning	Jun-Tao Tang, Yu-Cheng Shi, Zhen-Hao Xie	http://arxiv.org/abs/2605.26110v1	cs.LG, cs.CL	May 25, 2026	Detected	RDR86	Multimodal Large Language Models (MLLMs) achieve versatility by reformulating diverse tasks i...
InstructSAM: Segment Any Instance with Any Instructions	Yuqian Yuan, Wentong Li, Zhaocheng Li	http://arxiv.org/abs/2605.26102v1	cs.CV	May 25, 2026	None	RDR86	In this paper, we introduce InstructSAM, a unified and streamlined framework designed for mul...
DiscoverPhysics: Benchmarking LLMs for Out-of-the-Box Scientific Thinking	Matt L. Wiemann, Lindsay M. Smith, Peter Melchior	http://arxiv.org/abs/2605.26087v1	stat.ML, cs.LG	May 25, 2026	None	RDR86	Frontier LLMs now perform strongly across a wide range of physics evaluations, but it is hard...
StakeBench: Evaluating Language Understanding Grounded in Market Commitment	Yunhua Pei, Jingyu Hu, Yiwei Shi	http://arxiv.org/abs/2605.26074v1	cs.CL, cs.AI	May 25, 2026	None	RDR86	Existing financial NLP benchmarks often rely on labels supplied by outside observers, measuri...
Rethinking Weak Supervision in Anomaly Detection: A Comprehensive Benchmark	Xu Yao, Siyuan Zhou, Wu Zhenbo	http://arxiv.org/abs/2605.26068v1	cs.LG, cs.AI	May 25, 2026	Detected	RDR86	Weakly supervised anomaly detection (WSAD) has developed in three primary directions: incompl...
YoCausal: How Far is Video Generation from World Model? A Causality Perspective	You-Zhe Xie, Yu-Hsuan Li, Jie-Ying Lee	http://arxiv.org/abs/2605.30346v1	cs.CV	May 28, 2026	None	RDR85	As video diffusion models (VDMs) advance toward world models, a key question arises: do they...
SchGen: PCB Schematic Generation with Semantic-Grounded Code Representations	Qinpei Luo, Ruichun Ma, Xinyu Zhang	http://arxiv.org/abs/2605.30345v1	cs.AI, cs.CL	May 28, 2026	None	RDR85	Printed circuit board (PCB) schematic design defines nearly all electronic hardware, but it r...