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
HoloCount: A Holistic Visual Counting Benchmark for MLLMs	Jinhong Deng, Limeng Qiao, Guanglu Wan	http://arxiv.org/abs/2607.06420v1	cs.CV	Jul 7, 2026	None	RDR87	Visual counting is a fundamental pillar of multimodal intelligence, requiring a seamless inte...
An Experimental Design Approach to Evaluating Agentic AI's Autonomous Model Discovery	Hao He, Xueying Liu, Chris J. Kuhlman	http://arxiv.org/abs/2607.06413v1	stat.ME, cs.AI	Jul 7, 2026	None	RDR84	Large language model coding agents increasingly perform open-ended data modeling and analysis...
RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications	Evgeny Shilov	http://arxiv.org/abs/2607.06411v1	cs.SE, cs.AI	Jul 7, 2026	None	RDR87	Developers increasingly delegate real maintenance work to product-grade coding agents, and ma...
What Images Cannot Say: Language-Guided Olfactory Representation Learning	Eleftherios Tsonis, Xi Wang, Vicky Kalogeiton	http://arxiv.org/abs/2607.06402v1	cs.CV, cs.AI	Jul 7, 2026	None	RDR84	Images tell us what a scene looks like, but rarely what it would feel like to be there. While...
An Exact Instrument for State Usage in Selective State-Space Models, and the Input-Driven Migration It Reveals	Raktim Bhattacharya	http://arxiv.org/abs/2607.11796v1	cs.LG	Jul 13, 2026	None	RDR75	Selective state-space models such as Mamba route information through a bank of first-order mo...
Task-Specific Multimodal Question Answering Agents via Confidence Calibration and Incremental Reasoning for QANTA 2026	Nirjhar Das, Md. Al-Mamun Provath	http://arxiv.org/abs/2607.09623v1	cs.CL, cs.AI	Jul 10, 2026	None	RDR81	We present our submission to the QANTA 2026 shared challenge at the ICML 2026 Workshop on Eff...
Agora: Enhancing LLM Agent Reasoning Via Auction-Based Task Allocation	Kaiji Zhou, Ales Leonardis, Yue Feng	http://arxiv.org/abs/2607.09600v1	cs.AI, cs.CL	Jul 10, 2026	None	RDR79	Enhancing the reasoning capabilities of large language model (LLM) agents requires effective...
Geometry and Gradient-based Partitioning for Panoramic Outdoor Reconstruction	Weijian Chen, Weibo Yao, Yuhang Zhang	http://arxiv.org/abs/2607.08769v1	cs.CV	Jul 9, 2026	None	RDR77	Scaling 3D Gaussian Splatting (3DGS) to large outdoor scenes is costly in both data acquisiti...
Enhancing In-context Panoramic Generation via Geometric-aware Pretraining	Haoran Feng, Ruiyang Zhang, Longyi Zhang	http://arxiv.org/abs/2607.08765v1	cs.CV	Jul 9, 2026	None	RDR81	In this work, we present Canvas360, a two-stage framework for in-context panoramic generation...
Validity of LLMs as data annotators: AMALIA on authority	Manuel Pita	http://arxiv.org/abs/2607.08731v1	cs.CL, cs.AI	Jul 9, 2026	None	RDR81	A national language model offers a linguistic community its own instrument for measuring what...