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
VeriTrace: Evolving Mental Models for Deep Research Agents	Haolang Zhao, Yunbo Long, Lukas Beckenbauer	http://arxiv.org/abs/2605.26081v1	cs.AI	May 25, 2026	None	RDR78	Deep research agents face vast, interdependent, and pervasively uncertain information. Existi...
Sensor2Sensor: Cross-Embodiment Sensor Conversion for Autonomous Driving	Jiahao Wang, Bo Sun, Yijing Bai	http://arxiv.org/abs/2605.22809v1	cs.CV	May 21, 2026	None	RDR78	Robust training and validation of Autonomous Driving Systems (ADS) require massive, diverse d...
The Matching Principle: A Geometric Theory of Loss Functions for Nuisance-Robust Representation Learning	Vishal Rajput	http://arxiv.org/abs/2605.22800v1	cs.LG, cs.AI	May 21, 2026	None	RDR78	Robustness, domain adaptation, photometric and occlusion invariance, compositional generalisa...
REST3D: Reconstructing Physically Stable 3D Scenes from a Single Image	Xiaoxuan Ma, Jiashun Wang, Nicolas Ugrinovic	http://arxiv.org/abs/2605.30338v1	cs.CV	May 28, 2026	None	RDR77	Reconstructing physically stable 3D scenes from a single RGB image enables casual images to b...
Calibrating Conservatism for Scalable Oversight	William Overman, Mohsen Bayati	http://arxiv.org/abs/2605.28807v1	cs.AI	May 27, 2026	None	RDR77	Agentic AI systems capable of autonomous planning and extended environmental interaction pose...
Can LLMs Use Linguistic Uncertainty Markers to Reliably Reflect Intrinsic Confidence?	Gabrielle Kaili-May Liu, Arman Cohan	http://arxiv.org/abs/2605.28778v1	cs.CL	May 27, 2026	None	RDR77	LLMs' linguistically expressed confidence should faithfully reflect their intrinsic uncertain...
When Eyes Betray AI: Social Gaze Consistency as a Semantic Cue for AI-Generated Image Detection	Kim Jihyeon, Sohee Kim, Soosan Lee	http://arxiv.org/abs/2605.27348v1	cs.CV, cs.AI	May 26, 2026	None	RDR77	Recent generative models have largely closed the gap on low-level artifacts - pixel fingerpri...
Real Images, Worse Judgments: Evaluating Vision-Language Models on Concreteness and Imagery	Yifan Jiang, Ruoxi Ning, Sheng Yao	http://arxiv.org/abs/2605.27315v1	cs.CL	May 26, 2026	None	RDR77	Visual inputs are often assumed to improve language understanding in multimodal models. We ex...
MOSS: Self-Evolution through Source-Level Rewriting in Autonomous Agent Systems	Qianshu Cai, Yonggang Zhang, Xianzhang Jia	http://arxiv.org/abs/2605.22794v1	cs.AI, cs.LG	May 21, 2026	None	RDR77	Autonomous agentic systems are largely static after deployment: they do not learn from user i...
Deep Reinforcement Learning for Flexible Job Shop Scheduling with Random Job Arrivals	Yu Tang, Muhammad Zakwan, Efe Balta	http://arxiv.org/abs/2605.22773v1	cs.AI, math.OC	May 21, 2026	None	RDR77	The Flexible Job Shop Scheduling Problem (FJSP) is the optimal allocation of a set of jobs to...