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
In-Context Reward Adaptation for Robust Preference Modeling	Zhenyu Sun, Zheng Xu, Ermin Wei	http://arxiv.org/abs/2605.30323v1	cs.LG, cs.AI	May 28, 2026	None	RDR74	Reinforcement Learning from Human Feedback (RLHF) typically relies on static reward models to...
Personal Visual Memory from Explicit and Implicit Evidence	Viet Nguyen, Thao Nguyen, Vishal M. Patel	http://arxiv.org/abs/2605.28806v1	cs.CV, cs.CL	May 27, 2026	None	RDR74	Long-term memory is increasingly important for personalized AI agents, yet existing benchmark...
Human Label Variation as Stable Signal: Learning Annotator-Specific Explanation Behavior via Cross-Annotator Preference Optimization	Beiduo Chen, Pingjun Hong, Ziyun Zhang	http://arxiv.org/abs/2605.28802v1	cs.CL	May 27, 2026	None	RDR74	Free-text explanations extend human label variation (HLV) beyond label disagreement by reveal...
Agent Explorative Policy Optimization for Multimodal Agentic Reasoning	Minki Kang, Shizhe Diao, Ryo Hachiuma	http://arxiv.org/abs/2605.28774v1	cs.CL	May 27, 2026	None	RDR74	Vision-language models with extended reasoning succeed on complex problems, but many real-wor...
SwarmHarness: Skill-Based Task Routing via Decentralized Incentive-Aligned AI Agent Networks	Edwin Jose	http://arxiv.org/abs/2605.28764v1	cs.AI, cs.DC	May 27, 2026	None	RDR74	Vast quantities of compute (GPU cycles on personal workstations, idle inference servers, and...
Natural Language Query to Configuration for Retrieval Agents	Melissa Z. Pan, Negar Arabzadeh, Mathew Jacob	http://arxiv.org/abs/2605.27361v1	cs.AI, eess.SY	May 26, 2026	None	RDR74	Modern retrieval agents expose many configuration choices -- LLM, retriever, number of docume...
Towards Controllable Image Generation through Representation-Conditioned Diffusion Models	Nithesh Chandher Karthikeyan, Jonas Unger, Gabriel Eilertsen	http://arxiv.org/abs/2605.27343v1	cs.CV, cs.LG	May 26, 2026	None	RDR74	Diffusion models have emerged as powerful tools for high-quality image generation and editing...
FinHarness: An Inline Lifecycle Safety Harness for Finance LLM Agents	Haoxuan Jia, Yang Liu, Bin Chong	http://arxiv.org/abs/2605.27333v1	cs.CL	May 26, 2026	None	RDR74	Finance LLM agents must simultaneously block prompt-induced unauthorized actions and approve...
LLMs as Noisy Channels: A Shannon Perspective on Model Capacity and Scaling Laws	Xu Ouyang, Deyi Liu, Yuhang Cai	http://arxiv.org/abs/2605.23901v1	cs.LG, cs.AI	May 22, 2026	None	RDR74	Existing scaling laws for Large Language Models (LLMs), predominantly monotonic power laws, f...
SPACENUM: Revisiting Spatial Numerical Understanding in VLMs	Jianshu Zhang, Yijiang Li, Huifeixin Chen	http://arxiv.org/abs/2605.23898v1	cs.AI	May 22, 2026	None	RDR74	Vision-Language Models (VLMs) are increasingly deployed in embodied environments, where they...