Updated daily708 verified stories
Research News tracker.
Material AI papers, studies, datasets, evaluations, and scientific advances with direct links to the underlying research.
- 30stories this week
- 708sources cited
- 708verified timeline entries
Verified sourcing
Every story links to the strongest available evidence: original sources when available, otherwise clearly attributed reporting.
Plain English
What happened, why it matters, and what to watch — without the jargon.
No filler
When the signal is thin, we publish nothing rather than padding the feed.
More stories
9 storiesSecurity
Paper warns that LLM agents can recover deleted knowledge through tools
A new arXiv paper identifies a gap in LLM unlearning: an agent may stop recalling information from its weights but recover it through web search, retrieval or database tools. The authors propose a two-stage method to reduce both forms of recovery while preserving legitimate tool use.arxiv.orgSecurity
Researchers propose KFS-RAG defense against database leakage in retrieval systems
A new arXiv paper proposes replacing raw retrieved passages with compact, keyword-grounded facts to reduce the risk that prompt injections cause retrieval-augmented generation systems to expose sensitive database contents.arxiv.orgInnovation
MCite-RL proposes reinforcement learning framework for more reliable visual citations in multimodal RAG
An arXiv preprint introduces MCite-RL, a framework that uses iterative retrieval, reasoning, recursive image cropping and citation-focused reinforcement learning to improve both multimodal answers and the accuracy of their visual evidence links.arxiv.orgSecurity
Adversarial tests expose major gaps in LLM unlearning
A preprint reports that language models can appear to forget targeted information under ordinary tests while still recovering it under strategic adversarial prompts.arxiv.orgSecurity
Study finds language models can represent when they are being evaluated
An arXiv study reports that six language models contained linearly decodable signals associated with being evaluated, while those internal signals only partly matched what the models said. The authors say steering along probe-derived directions changed verbalization scores, raising questions about how reliably…arxiv.orgInnovation
FCPRAG paper reports more stable fusion of retrieved evidence in parametric RAG
A paper accepted to EMNLP 2026 proposes FCPRAG, a controller that selectively combines passage-specific LoRA adapters in parametric retrieval-augmented generation. The authors report higher F1 scores than standard and parametric RAG baselines across four question-answering datasets, with gains of up to 7.55%.arxiv.orgInnovation
Study finds more GPU resources do not reliably translate into greater NLP research impact
An analysis of 13,921 papers from major NLP conferences found that the papers reporting the most GPU capability captured most reported resources but only a minority of citations and awards. The study found a statistical association between compute and scholarly impact, but little standalone explanatory power.arxiv.orgProduct
chemeurope.com reports Skala AI model is now available in CP2K
chemeurope.com reports that Microsoft Research’s Skala AI model has been integrated into the open-source CP2K simulation ecosystem, giving researchers access to an AI-based exchange-correlation functional for quantum-mechanical simulations. The outlet says initial testing showed improved accuracy in a specific test…chemeurope.comInnovation
PUMA benchmark tests whether multimodal AI understands Polish culture
An arXiv preprint introduces PUMA, a 900-task benchmark for evaluating multimodal AI in Polish cultural and linguistic contexts, reporting strong visual question-answering performance but substantial weaknesses in complex audio and document understanding.arxiv.org
One useful briefing each week
Keep up with AI without living in the feed.
Get the week’s verified AI news, original data, useful tools, learning picks, and fresh AI jobs.
Reach people who are learning AI
Hiring an AI professional or launching a useful AI product? Put it in front of people who came here to learn and act.
Post an AI jobSubmit an AI tool