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/2608.26086v1

Code links

on this page

Paper	Authors	arXiv ID	Categories	Published	Code	Radar	Summary
TraceML: An Empirical Analysis of Human-Agent Planning in Machine Learning Development	Jiarui Yan, Weiwei Sun, Sijie Li	http://arxiv.org/abs/2608.26086v1	cs.LG, cs.AI	Aug 26, 2026	Detected	RDR86	Large language models write correct code for isolated problems but remain far weaker at auton...
WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution	Liyan Tang, Cyrus Rashtchian, Chun-Sung Ferng	http://arxiv.org/abs/2608.27454v1	cs.AI, cs.CL	Aug 27, 2026	None	RDR75	Agent skills package specialized knowledge and workflows into reusable resources that extend...
SWE-Prime: Fewer Trajectories, Better Performance	Dewu Zheng, Ruizhe Ye, Yanlin Wang	http://arxiv.org/abs/2608.27449v1	cs.SE, cs.AI	Aug 27, 2026	None	RDR81	To improve large language models' ability to resolve real-world software issues, prior work h...
From Static to Dynamic: Benchmarking Real-World Code Review with MCR-Bench	Dewu Zheng, Yanlin Wang, Xiwen Wang	http://arxiv.org/abs/2608.27442v1	cs.SE, cs.AI	Aug 27, 2026	None	RDR81	In real-world software development, code review typically involves iterative interactions bet...
Beyond F1: Evaluating Coverage and Failure Recovery in AI Model Security Scanners	Qianlong Lan, Vinothini Pandurangan, Anuj Kaul	http://arxiv.org/abs/2608.27424v1	cs.CR, cs.AI	Aug 27, 2026	None	RDR82	Static scanners are increasingly used to identify executable or otherwise unsafe content in m...
Consolidating RLVR Capabilities Across Domains: A Deep Dive into Fusion Paradigms	Siye Wu, Kai Yang, Yuchen Cai	http://arxiv.org/abs/2608.27409v1	cs.CL	Aug 27, 2026	None	RDR80	Reinforcement learning with verifiable rewards (RLVR) improves specific capabilities of large...
CorporateBench: Large-Scale Q&A Benchmarking with Temporal Knowledge Bases	Sil Hamilton, Albert Yu Sun, Oscar J. Romero	http://arxiv.org/abs/2608.27391v1	cs.AI, cs.CL	Aug 27, 2026	None	RDR87	LLMs are increasingly able to answer complex questions about enterprise-scale document collec...
D2C-Routing: Dimension-to-Composition Evidence Routing for Mixed-Origin AI-Generated Text Detection	Xin Chen, Fuwei Zhang, Yiqi Tong	http://arxiv.org/abs/2608.27380v1	cs.CL	Aug 27, 2026	Detected	RDR86	AI-generated text detection is commonly framed as a binary document-level judgment about whet...
VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning	Junxiang Xu, Ruisi Wang, Fanyi Pu	http://arxiv.org/abs/2608.26105v1	cs.CV, cs.AI	Aug 26, 2026	None	RDR86	Native visual reasoning treats visual generation as the medium of reasoning itself: visual st...
TTPO: Test-Time Policy Optimization	Aozhe Wang, Zhengxi Lu, Jianze Wang	http://arxiv.org/abs/2608.27448v1	cs.CL	Aug 27, 2026	None	RDR74	Recent prominent post-training methods, such as Reinforcement Learning (RL) and On-Policy Sel...