Updated daily711 verified stories
Research News tracker.
Material AI papers, studies, datasets, evaluations, and scientific advances with direct links to the underlying research.
- 31stories this week
- 711sources cited
- 711verified 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 storiesInnovation
SAGE proposes a lower-cost way to evaluate task-oriented AI dialogue agents
A new arXiv preprint introduces SAGE, an evaluation system that checks whether each turn in a task-oriented AI conversation correctly advances the underlying workflow state. The authors report that its core version matched or exceeded evaluated LLM judges across four benchmark slices while using symbolic rules and…arxiv.orgSecurity
Study finds answer-aware AI monitors can miss flawed reasoning
A preprint reports that giving AI monitors a trusted answer improved their ability to detect wrong conclusions but reduced their ability to identify errors hidden inside correct solutions.arxiv.orgInnovation
RestoreBench tests whether AI agents can restore power-flow convergence
A new arXiv benchmark evaluates chatbot, single-agent and multi-agent LLM systems on diagnosing and correcting non-convergent power-flow cases across two power grids.arxiv.orgInnovation
Preprint describes AI system rebuilding service-marketplace matching taxonomies across 132 occupations
A new arXiv preprint describes an autoresearch loop deployed since April at an unnamed major U.S. consumer-services marketplace to generate provider-preference taxonomies for AI-based matching across 132 occupations.arxiv.orgInnovation
Dr. Claw adds audit trails and recovery to AI research workflows
A new open-source workspace wraps coding agents in a human-controlled workflow designed to make AI-assisted research more traceable and recoverable.arxiv.orgInnovation
Gated-memory routing aims to reduce the cost of multi-agent LLM systems
A newly submitted paper proposes retaining only useful reasoning steps when multiple language-model agents collaborate. Its abstract reports higher average benchmark accuracy and a 31.9% reduction in HumanEval inference cost compared with the strongest baseline.arxiv.orgSecurity
Study finds AI deception signals transfer unevenly between test settings
An arXiv study of Llama-3.1-70B-Instruct reports that spontaneous and instructed deception share some internal direction, but detection and steering methods transfer asymmetrically between them.arxiv.orgInnovation
Paper proposes versioned contracts to keep AI agent memory from going stale
A new arXiv paper reports that version stamps and row-level eviction can help AI agents reuse recovery advice after server-side changes without silently applying outdated fixes.arxiv.orgInnovation
Conversation Coach brings voice-based AI rehearsal to difficult workplace conversations
A new arXiv paper describes Conversation Coach, a voice-first AI system for managers practicing difficult workplace conversations. Its production deployment reportedly reached more than 40,000 managers over six months, while the authors found a trade-off between the speed and cost of end-to-end speech-to-speech…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