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/2608.24848v1

Code links

on this page

Paper	Authors	arXiv ID	Categories	Published	Code	Radar	Summary
BrowserForge: Scaling Web Episode via Parallel Browser Sandboxes	Fei Tang, Huawen Shen, Zhiqiong Lu	http://arxiv.org/abs/2608.24848v1	cs.CL	Aug 25, 2026	None	RDR76	Web agents that act from rendered pixels avoid the fragility and heavy token cost of reading...
StarHarness: Evolving Harnesses with Stratified Search for Enterprise Environments	Esakkivel Esakkiraja, Denis Akhiyarov, Vikas Yadav	http://arxiv.org/abs/2608.24804v1	cs.AI, cs.SE	Aug 25, 2026	None	RDR77	We present StarHarness, a framework for evolving environment-specific agent harnesses while k...
CAFE: Self-Improving Search Agents Need Co-Evolving Feedback	Boyang Liu, Senjie Jin, Peixin Wang	http://arxiv.org/abs/2608.24794v1	cs.AI	Aug 25, 2026	None	RDR78	Outcome-supervised search agents learn when and how to retrieve evidence, but terminal reward...
Image Difference Quantification Using Autoencoder-Based Latent Representations	Manish Sharma, Timothy Yim, Clifton Forlines	http://arxiv.org/abs/2608.24782v1	cs.CV	Aug 25, 2026	None	RDR84	Traditional image similarity metrics such as Mean Squared Error (MSE), Peak Signal-to-Noise R...
Stochastic Estimation of Transduced Language Models	Vésteinn Snæbjarnarson, Samuel Kiegeland, Manuel de Prada Corral	http://arxiv.org/abs/2608.27428v1	cs.CL	Aug 27, 2026	None	RDR73	Transduced language models (TLMs) compose a pretrained \emph{source} language model with a fu...
ICON Decomposition: Multivariate Concept-Level Explanations of Deep Representations for Model Auditing	Roshan Prakash Rane, Marco Simnacher, Manuel Pfeuffer	http://arxiv.org/abs/2608.26083v1	cs.LG, cs.AI	Aug 26, 2026	None	RDR80	Deep neural networks often exploit spurious associations in their training data, a failure kn...
Fine-Tuning Whisper for Automatic Speech Recognition in Baniwa: A Preliminary Study	Leonardo Duart, Tiago Fonseca, Thiago Chacón	http://arxiv.org/abs/2608.26060v1	cs.CL, stat.ML	Aug 26, 2026	None	RDR79	Automatic Speech Recognition (ASR) technologies have achieved remarkable performance in recen...
Beyond Local Surprise: Grounded Dialogue as Selective Belief Revision under Referential Uncertainty	Ziming Liu, Bhanu Chaitanya Jasti, Ziyang Xu	http://arxiv.org/abs/2608.26035v1	cs.CL	Aug 26, 2026	None	RDR74	When a speaker refers to a scene that the listener cannot directly see, the listener must dec...
Do Robotic World Models Really Follow Actions? Diagnosing and Aligning Action-Conditioned Generation for Policy Learning	Sixiang Chen, Jiaming Liu, Jixian Wu	http://arxiv.org/abs/2608.24885v1	cs.RO, cs.CV	Aug 25, 2026	None	RDR79	Action-conditioned world models are increasingly used as learned simulators for policy evalua...
What FID Hides: Detecting, Ranking, and Diagnosing Deviations in Generative Evaluation	Hao Chen	http://arxiv.org/abs/2608.24881v1	stat.ML, cs.LG	Aug 25, 2026	None	RDR83	Generative models are commonly ranked by Fréchet Inception Distance (FID) and Kernel Inceptio...