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

3,367

matching records

Shown

current page

Top radar

http://arxiv.org/abs/2610.12463v1

Code links

on this page

Paper	Authors	arXiv ID	Categories	Published	Code	Radar	Summary
From Reactive Containment to Proactive Assurance: Lessons from OpenAI, Anthropic, and Google Agent Security Incidents	Abbas Raftari	http://arxiv.org/abs/2610.12463v1	cs.CR, cs.AI	Oct 8, 2026	None	Score75	In 2026, cybersecurity evaluations involving OpenAI, Anthropic, and Google agents reached rea...
Pumpire: Unified Benchmark for Metric Distance Estimation	Siyu Chen, Zehan Wang, Jiayang Xu	http://arxiv.org/abs/2610.12423v1	cs.CV	Oct 8, 2026	None	Score82	We present Pumpire, a unified benchmark for evaluating metric point-pair distance estimation...
Validity Without Ground Truth: What Stated-Preference Economics Offers the Evaluation of Language Models	Daniel Robert Kling Alexander, Catherine Louise Kling	http://arxiv.org/abs/2610.10506v1	cs.AI, cs.CL	Oct 7, 2026	None	Score78	Many of the questions now put to large language models have no correct answer to score agains...
EmbodiedRSI: Active Continual Robot Learning Through Hypothesis-Guided Co-Evolution	Python Song, Zhixuan Liang, Kelsey Fu	http://arxiv.org/abs/2610.10498v1	cs.AI	Oct 7, 2026	None	Score79	Robot foundation models provide strong visuomotor control, yet their performance can degrade...
Agentic RSR: Real-to-Sim-to-Real through Scene Reconstruction and Execution-Grounded Robot Policies	Yihan Li, Yating Feng, Shengjiu Sun	http://arxiv.org/abs/2610.10479v1	cs.RO, cs.CV	Oct 7, 2026	None	Score73	A simulation of a real robot workspace must preserve task-relevant interactions, while polici...
World Models' Last Exam in Physics	Mingju Gao, Qingle Liu, Yuzhao Peng	http://arxiv.org/abs/2610.08791v1	cs.CV	Oct 6, 2026	None	Score81	Video world models can produce visually convincing yet physically inconsistent sequences, rai...
VeriFine: Scaling Verification for Self-Improvement in Embodied Reasoning	Zewei Zhou, Rachel Luo, Yulong Cao	http://arxiv.org/abs/2610.08761v1	cs.AI, cs.RO	Oct 6, 2026	None	Score81	Self-improving policies continually expose new failure patterns, changing what their judges m...
WorldSonus: Bringing Sound to Worlds	Pengjun Fang, Jingyi Fa, Kam Man Wu	http://arxiv.org/abs/2610.08760v1	cs.SD, cs.AI	Oct 6, 2026	None	Score80	Recent advances in world models have enabled increasingly realistic visual synthesis. However...
One Figure, Every Canvas: Editable Flowchart Relayout via Agentic Pipeline	Shih-Chen Tseng, Chih-Hsuan Chen, Ryan Yang	http://arxiv.org/abs/2610.06852v1	cs.CV, cs.AI	Oct 5, 2026	None	Score81	Pipeline figures in ML papers must be repurposed across many canvases, including paper column...
MemPilot: Orchestrating On-Demand Multimodal Memory Curation for LLM Agents	Haozhen Zhang, Haodong Yue, Quanyu Long	http://arxiv.org/abs/2610.06830v1	cs.CL, cs.AI	Oct 5, 2026	None	Score75	Memory has become integral to the LLM agent ecosystem, supporting information retention and r...