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/2610.13889v1

Code links

on this page

Paper	Authors	arXiv ID	Categories	Published	Code	Radar	Summary
RATED: Reliability-Aware AI Agent Tool Retrieval via Execution Dynamics	Weiliang Chen, Song Liao	http://arxiv.org/abs/2610.13889v1	cs.AI, cs.IR	Oct 9, 2026	Detected	Score85	As AI agents increasingly rely on external tools, accurate retrieval is essential for reliabl...
Can Language Models Play the Wikipedia Game?	Alexander Hickey, Joanna Knight, James Bishop	http://arxiv.org/abs/2610.13948v1	cs.AI, cs.IR	Oct 9, 2026	None	Score85	Language models increasingly support or automate information retrieval from document collecti...
RSI-Anything: Unlocking Recursive Self-Improvement with World Models	Taoyong Cui, Pinxian Zeng, Wanghan Xu	http://arxiv.org/abs/2610.13912v1	cs.CL	Oct 9, 2026	None	Score82	Recursive self-improvement (RSI) aims to transform interaction experience into persistent imp...
Revisiting Tabular Deep Regression: Objectives and the Limits of Global Early Stopping	Danil Rudenko, Georgii Bulgakov, Nikolay Kartashev	http://arxiv.org/abs/2610.13909v1	cs.LG, cs.AI	Oct 9, 2026	Detected	Score85	While deep learning models for tabular data have recently received significant research atten...
Images Talk Back: Guiding MMDiTs by Suppressing Image-to-Text Feedback	Yucheng Yang, Xiaoxiao Sun, Shusheng Yang	http://arxiv.org/abs/2610.13941v1	cs.CV	Oct 9, 2026	Detected	Score84	Multimodal diffusion transformers (MMDiTs) allow the evolving image to update internal text r...
When VLMs Destroy What They Know: Spatial Representations Fall Below Lexical Priors	Shubh Garg, Chen Shani	http://arxiv.org/abs/2610.13910v1	cs.CL	Oct 9, 2026	None	Score85	Vision-Language Models (VLMs) increasingly analyze and reason about images, yet it remains un...
Towards Physically Grounded Articulated 3D Assets: A Multi-Agent Pipeline and Benchmark	Xudong Cai, Ruijie Zhu, Haoliang Shang	http://arxiv.org/abs/2610.13947v1	cs.CV	Oct 9, 2026	None	Score78	In this paper, we study physically grounded articulated 3D asset generation---moving the goal...
X-AgentRed: Red-Teaming Personal Agents in Evolving Multi-Service Ecosystems	Yeonsung Jung, Zhiyuan Wang, Zifan Wang	http://arxiv.org/abs/2610.13886v1	cs.AI	Oct 9, 2026	None	Score73	Personal agents increasingly connect to services across the web and applications by using too...
Can machines reason non-verbally?	Shaheer U. Saeed, Zion Tse, Gregory Slabaugh	http://arxiv.org/abs/2610.13925v1	cs.CV	Oct 9, 2026	None	Score78	Modern machines can solve equations, follow logic and reason through language, yet they still...
Beyond the Snowflakes: Disentangling Weather Effects from Confounding Meta-Factors in LiDAR Object Detection	Yiming Yang, Jeremy P. Bos	http://arxiv.org/abs/2610.13891v1	cs.CV, cs.RO	Oct 9, 2026	None	Score79	Light Detection and Ranging (LiDAR) is critical for autonomous perception, yet its performanc...