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

1,230

1 arXiv sources

Top radar

http://arxiv.org/abs/2607.11862v1

Published 24h

by paper date

Rate limit

1/3s

arXiv policy

Paper	Authors	arXiv ID	Categories	Published	Code	Radar	Summary
Finding H. pylori in the Fine Print: Evidence-Linked Multi-Agent Case Finding from Gastric Biopsy Reports	Yufan Wang, Anit Kumar Sahu, Yan Fei Ng	http://arxiv.org/abs/2607.06435v1	cs.AI	Jul 7, 2026	None	RDR84	Data from Singapore indicated that about 31% of the population had evidence of Helicobacter p...
VEXAIoT: Autonomous IoT Vulnerability EXploitation using AI Agents	Katherine Swinea, Kshitiz Aryal, Lopamudra Praharaj	http://arxiv.org/abs/2607.09653v1	cs.CR, cs.AI	Jul 10, 2026	None	RDR72	Internet of Things (IoT) systems are inherently vulnerable due to constrained hardware, outda...
Entropy-Constrained Machine Learning with Residual Data Augmentation for Modeling Chemical Kinetics	Okezzi Ukorigho, Opeoluwa Owoyele	http://arxiv.org/abs/2607.09582v1	physics.flu-dyn, cs.LG	Jul 10, 2026	None	RDR80	We present a physics-constrained machine learning framework for accelerating the direct numer...
OpenCoF: Learning to Reason Through Video Generation	Xinyan Chen, Ziyu Guo, Renrui Zhang	http://arxiv.org/abs/2607.08763v1	cs.CV, cs.AI	Jul 9, 2026	None	RDR82	Reasoning has become a core capability for large models, especially when reliable decisions r...
Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation	Yifan Zhou, Qihao Yang, Yan Li	http://arxiv.org/abs/2607.08758v1	cs.AI	Jul 9, 2026	None	RDR79	Scientific ideas rarely start from a blank page. They inherit mechanisms, repair known limita...
SLORR: Simple and Efficient In-Training Low-Rank Regularization	David González-Martínez, Shiwei Liu	http://arxiv.org/abs/2607.08754v1	cs.LG, cs.AI	Jul 9, 2026	None	RDR72	Low-rank factorization is widely used to compress neural networks, but modern models are ofte...
AUTOPILOT VQA: Benchmarking Vision-Language Models for Incident-Centric Dashcam Understanding	Siddharth Damodharan, Radhika Gupta, Ali Alshami	http://arxiv.org/abs/2607.08745v1	cs.AI, cs.CV	Jul 9, 2026	None	RDR81	Recent advances in Vision-Language Models, Large Language Models, and Multimodal Large Langua...
Workflow as Knowledge: Semantic Persistence for LLM-Mediated Workflows	Emanuele Quinto, Carlo Andrea Rozzi, Francesco Zanitti	http://arxiv.org/abs/2607.08740v1	cs.AI, cs.PL	Jul 9, 2026	None	RDR80	Large language model (LLM) applications increasingly use explicit workflows for tool use, ret...
The Key to Going Linear: Analysis-Driven Transformer Linearization	Anna Kuzina, Paul N. Whatmough, Babak Ehteshami Bejnordi	http://arxiv.org/abs/2607.07706v1	cs.LG	Jul 8, 2026	None	RDR78	The quadratic cost of causal self-attention severely bottlenecks long-context transformer inf...
Agon: Competitive Cross-Model RL with Implicit Rival Grading of Reasoning	Vladislav Beliaev	http://arxiv.org/abs/2607.07690v1	cs.LG, cs.AI	Jul 8, 2026	None	RDR76	Reinforcement learning from verifiable rewards (e.g. GRPO) is the engine behind today's reaso...