Updated daily397 verified stories
Material AI papers, studies, datasets, evaluations, and scientific advances with direct links to the underlying research.
Every story links to the strongest available evidence: original sources when available, otherwise clearly attributed reporting.
What happened, why it matters, and what to watch — no jargon tax.
When the signal is thin, we publish nothing rather than padding the feed.
A growing stream of verified perspectives for people who need to understand AI without chasing hype.
A paper introduces THPT-Ladder, a 632-item benchmark that applies Vietnam’s 2025 national exam grading scheme to language models and reports materially different scores from standard proportional-accuracy measures.
An arXiv paper describes how Netflix built, deployed and continuously monitored an LLM judge for recommendation explanations, reporting viewing and engagement gains in a five-week A/B test involving tens of millions of members.
A new arXiv survey proposes viewing an AI agent’s memories, tools, skills, workflows and relationships as a graph that changes over time, and calls for graph-aware evaluation and governance.
A new arXiv preprint presents FACET, a framework for generating executable terminal tasks whose instructions, environments, solutions and verifiers are designed to remain consistent.
An arXiv preprint introduces SESSE, a training-free framework that breaks an LLM judge’s preference into sub-questions. The authors report near-parity with a chain-of-thought baseline on 1,000 RewardBench examples and criterion-level vote records; generalization, cost, and independent validation remain open questions.
An Apple research paper describes a three-phase iterative pseudo-labeling method for Mandarin-English code-switching automatic speech recognition and reports Mix Error Rate reductions on two SEAME development subsets.
MIT researchers report a density-functional-theory and machine-learning approach for identifying catalyst alloys that could improve electrochemical ammonia production, though the proposed materials have not yet been made or tested.
An arXiv preprint reports that code agents can perform differently on semantically equivalent codebases, with effects varying by model, agent framework and benchmark.
This study presents an enhanced model combining Fuzzy Logic with the IEEE Key Gas Method (FL-KGM) that introduces refined membership functions, optimized fuzzy rule sets, and a novel separation of CO and CO2 to eliminate diagnostic inconsistencies.
An arXiv study evaluates looped and conventional language models on three tool-calling benchmarks, reporting stronger results on workflows that require multiple dependent API calls and a potentially more efficient adaptive-computation approach.
A new arXiv paper proposes a three-agent code-review protocol in which a reviewer evaluates an agent’s code and a critic audits that review before edits are made. The authors report improved benchmark results over tested baselines, while also identifying false consensus as a failure mode.
An arXiv preprint compares zero-shot and parameter-efficient fine-tuning for hate-speech detection in Roman Urdu. The authors report that LoRA adaptation raised F1 performance from 0.56 to above 0.93 on a corpus containing more than 72,000 annotated comments.
One useful briefing each week
Get the week’s verified AI news, original data, useful tools, learning picks, and fresh AI jobs.
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 job Submit an AI tool