AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsTo Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents
arXiv:2605.18882v2 Announce Type: replace-cross Abstract: LLM agents exhibit a consistent tendency to over-call, invoking tools even in situations where none is needed. On the When2Call benchmark, six models from three f…
- arXiv cs.AIresearchReinforcement Learning over Predictive Distributions for LLM Regression
arXiv:2605.20740v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have emerged as flexible regressors capable of predicting real-valued quantities from heterogeneous inputs. Yet most LLM regression o…
- arXiv cs.AIresearchD3S2: Diffusion-Guided Dataset Distillation for Semantic Segmentation
arXiv:2605.25022v2 Announce Type: replace-cross Abstract: Dataset distillation (DD) aims to compress large-scale datasets into compact synthetic sets while preserving training efficacy. However, existing studies mainly f…
- arXiv cs.AIresearchSeeing Isn't Knowing: Do VLMs Know When Not to Answer Spatial Questions (and Why)?
arXiv:2605.30557v2 Announce Type: replace-cross Abstract: Spatial reasoning benchmarks typically evaluate whether vision-language models can derive the correct answer from a visual observation. Yet in real 3D environment…
- arXiv cs.AIresearchThe Terminal Representation in Reinforcement Learning
arXiv:2605.31289v3 Announce Type: replace-cross Abstract: Representation learning is a powerful tool for spatio-temporal abstraction within reinforcement learning (RL). Two well established approaches are through the suc…
- arXiv cs.AIagentsTask diversity produces systematic transfer but inhibits continual reinforcement learning
arXiv:2606.00880v2 Announce Type: replace-cross Abstract: Continual reinforcement learning (RL) aims to produce agents that never stop adapting to new tasks. A key question is how this interacts with the diversity of tas…
- arXiv cs.AIresearchFFR: Forward-Forward Learning for Regression
arXiv:2606.03927v2 Announce Type: replace-cross Abstract: The Forward-Forward (FF) algorithm offers a computationally efficient and biologically plausible alternative to backpropagation (BP) by training neural networks t…
- arXiv cs.AIresearchCharacterize Then Distill: Mechanistic Reasoning in Large Output Spaces
arXiv:2606.06840v4 Announce Type: replace-cross Abstract: Reasoning-trained language models can select, zero-shot, a small set of relevant labels from thousands to hundreds of thousands of candidates. We ask how they do…
- arXiv cs.AIresearchSensitivity Shaping for Latent Modeling
arXiv:2606.14585v2 Announce Type: replace-cross Abstract: Generative dynamics models enable planning in challenging systems, but safe deployment requires detecting policy-induced out-of-distribution (OOD) transitions. Ex…
- arXiv cs.AIresearchSAE++: Cascaded Sparse Autoencoders Learn Multi-Level Visual Concepts in Multimodal LLMs
arXiv:2606.16193v3 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have demonstrated strong performance on vision-language tasks, yet their internal visual representations remain difficult…
- arXiv cs.AIresearchExplaining Attention with Program Synthesis
arXiv:2606.19317v3 Announce Type: replace-cross Abstract: A longstanding goal of research on interpretable deep learning is to replace opaque neural computations with human-meaningful symbolic descriptions. In this paper…
- arXiv cs.AIresearchPrime Fourier Embeddings: A Principled Basis for Modular Arithmetic
arXiv:2606.23044v3 Announce Type: replace-cross Abstract: Numbers have algebraic structure that standard neural embeddings often fail to expose. We introduce Prime Fourier Embeddings (PFE), which encode integers as prime…
- arXiv cs.AIresearchGuided Action Flow: Value-Guided Sampling for Frozen Vision-Language-Action Policies
arXiv:2607.02092v4 Announce Type: replace-cross Abstract: Reinforcement learning can improve vision-language-action (VLA) policies beyond supervised fine-tuning, although this typically involves further updates to the po…
- arXiv cs.AIresearch3D-DefectBench: A Controlled Factorial Study of Vision-Language Model Evaluation Pipelines for Fine-Grained 3D Generation Defects
arXiv:2607.10826v2 Announce Type: replace-cross Abstract: Automated evaluation is essential for scaling generative 3D systems, where exhaustive human review is costly and slow. Yet the reliability of an automated judge d…
- arXiv cs.AIresearchRetrieval-Augmented Interpretable Learning: Towards Task-Specific Zero-Shot Models in Healthcare
arXiv:2607.17508v3 Announce Type: replace-cross Abstract: We introduce Retrieval-Augmented Interpretable Learning (RAIL), a probabilistic meta-learning framework for zero-shot generation of task-specific interpretable mo…
- arXiv cs.AIresearchVariational-Ising-Attention:Tailored Attention Matters for Science
arXiv:2607.23634v2 Announce Type: replace-cross Abstract: Attention enables context modeling via query-key scoring with softmax normalization. Driven by industrial long-context demands, mainstream research has converged…
- arXiv cs.AIresearchMulti-Scale Structural Features for Continual, Comprehensible Visual Recognition in a Developmental Learning Framework
arXiv:2607.25531v2 Announce Type: replace-cross Abstract: Contemporary machine learning struggles to learn continually, reuse prior knowledge, and expose a comprehensible internal structure. A recently proposed developme…
- arXiv cs.AIresearchDiagnosing Fine-Grained Inconsistency Classification in Financial Disclosure Text
arXiv:2607.26368v3 Announce Type: replace-cross Abstract: Financial disclosures may contain numerical, temporal, referential, factual, and policy inconsistencies that require different evidence and reasoning to diagnose.…
- arXiv cs.AIagentsStrategic Evaluation of Planning Strategies for LLM Agents in Cyber-Physical Systems
arXiv:2608.04265v2 Announce Type: replace-cross Abstract: LLM-agent evaluations commonly measure task success or agreement with a declared plan. In strategic cyber-physical systems, an architecture must also remain appro…
- arXiv cs.AIresearchDo AI weather models miss extremes?
arXiv:2608.09972v2 Announce Type: replace-cross Abstract: AI weather models are often reported to underestimate extremes, but most evidence concerns deterministic regression models verified against reanalysis. We evaluat…
- arXiv cs.AIresearchPertMind: Eliciting Emergent Biological Reasoning in LLM via Reinforcement Learning on Cellular Perturbation Data
arXiv:2608.16419v3 Announce Type: replace-cross Abstract: Large language models can describe mechanisms, yet scalable post-training still depends on costly, manually curated biological reasoning traces. Here we show that…
- arXiv cs.AIresearchThe Latent Diagnostic Taxonomy: A Framework for Constructing Classifiers and Diagnosing Their Decisions, Applied to Prompt Injection Detection
arXiv:2608.26423v2 Announce Type: replace-cross Abstract: This paper proposes a framework for constructing a classifier as a safeguard layer, and for developing a complementary diagnostic that identifies which of the cla…
- arXiv cs.AIagentsCost-Aware Hierarchical Multi-Agent Ransomware Detection and Family Attribution under Analysis Budgets
arXiv:2609.04820v2 Announce Type: replace-cross Abstract: Sandbox execution and memory forensics are among the most constrained resources in malware triage. Static analysis can scale to millions of files, whereas dynamic…
- AI BusinessmodelsReflection’s Beam model signals deepening split in global AI market
The U.S. startup holds an advantage in the open-weight market due to its funding and technology relationship with Nvidia.
- LessWrongresearchChallenging the unawareness argument with third actions and mixed actions
[ x-posted from the EA Forum ] 1. Introduction Here’s Anthony DiGiovanni’s unawareness argument, quoted from his summary post (footnotes omitted): Let’s say that we c-prefer A over B if the reason we prefer A is an impar…
- The Register AI + MLpolicySouth Korean president calls for creation of tools that stop all cyber-attacks
'Complete security paradigm refresh' needed for the AI era
- Engadget AIagentsCisco is bringing a new agentic framework to its Webex enterprise platform
Cisco's Dialog feature promises to turn "fragmented interactions into continuous customer relationships."
- Engadget AIsafetyGoogle's AI detection website is now available
SynthID Detector will flag content created with AI tools from OpenAI, Google, Apple and other companies.
- SiliconANGLE AIagentsCaterpillar and CoreWeave shorten the learning loop for physical AI
Demand for new data centers, power plants and highways is fueling a construction boom, even as the industry wrestles with declining productivity and a shortage of skilled machine operators. Physical AI, which lets machin…
- AI BusinessagentsHumanoid hard sell: Building robots for the manufacturing age
Where humanoid publicity outpaces reality, why purpose-built machines deserve more attention and how the West can get automation onto the factory floor.
- Engadget AIresearchOpenAI just posted hundreds more results on major math problems
The company said that most results were produced in a response to a single prompt given to a single AI agent.
- Guardian AIpolicyOpenAI came to Australia to apologise. It will leave without answering these key questions | Toby Walsh
We don’t accept drugs killing a few people because they cure most patients. Or a few planes crashing because most land safely. AI should be no different OpenAI’s CEO Sam Altman was asked to appear before the Joint Select…
- SiliconANGLE AIagentsMeta teams up with Bret Taylor’s Sierra Technologies on new standards for AI agent commerce
Meta Platforms Inc. is partnering with Walmart Inc., Stripe Inc. and the enterprise artificial intelligence firm Sierra Technologies Inc. on the creation of new standards that will define how autonomous AI agents interac…
- TechRadar AIpolicyAWS warns 100 proposed data center bans could hurt America for generations
Mainstream AI news from a large tech publication.
- Guardian TechnologypolicyPornhub returns to Australia after banning access due to age verification rules
Australian adults again able to access the world’s most popular porn site after parent company introduces age checking via Apple devices Get our breaking news email , free app or daily news podcast Australian adults will…
- Simon Willison's WeblogagentsOpenAI “rogue” agent activities found on Wikimedia projects
OpenAI “rogue” agent activities found on Wikimedia projects Given how tempting a target wikis are for rogue agent swarms, it's not a huge surprise that Wikipedia found evidence of that activity once they went looking: Th…
- Engadget AImodelsGoogle's experimental Playground platform uses AI to create games for you
Google launches an AI-powered game creation platform called Playground.
- NVIDIA Developer BlogchipsFaster Scientific Image Analysis with NVIDIA cuPhoton
Observatories and telescopes, lasers and X-ray light sources, and other high-throughput instruments generate image data faster than CPU-bound pipelines can...
- The Verge AIsafetyChatGPT for Teens is an ‘unacceptable risk,’ says Common Sense Media
Common Sense Media, a nonprofit that offers reviews of apps, services, and entertainment with a focus on youth safety, today said that OpenAI's ChatGPT for Teens is an "unacceptable risk." ChatGPT for Teens, introduced i…
- Guardian TechnologycommunityJaguar targets young Americans with Type 01 EV – but it’s too long for UK parking spaces
Latest model is launching in New York to target rich US buyers – and is more than 5.2 metres long and 2 metres wide It has no rear window, will not fit into a UK parking space and – starting at £130,000 – ($172,000) is a…
- OpenAI NewsmodelsGPT-6 and Intelligent UI for everyone
GPT‑6 is rolling out globally in ChatGPT with Intelligent UI, delivering faster responses with visuals and interactive experiences you can explore and use directly.
- Simon Willison's WeblogsafetyQuoting Victoria Kim
Since the Medicare breach, OpenAI has put in place additional monitoring to allow “immediate intervention” by staff to stop training if the company’s models access the internet in ways they’re not supposed to, Mr. Kwon […
- The Verge AIresearchOpenAI drops another batch of mathematical breakthroughs
OpenAI has revealed solutions to a number of long-standing mathematics problems produced by an unreleased frontier model in a batch of 722 manuscripts, covering 372 result families that group related papers. It extends a…
- Simon Willison's Weblogopen-sourcellm-openai-decisions 0.1a0
Release: llm-openai-decisions 0.1a0 OpenAI released their new Jev-style Decisions API , as previously announced at last week's DevDay. Since I already have an llm-typesafe plugin for talking to Jev, I had GPT-6 Astra rea…
- Guardian AIpolicyPrivacy watchdog launches investigation into China-based company behind Kmart ‘pervert glasses’ app
Commissioner says Shenzhen Qingcheng, the app maker behind the HeyCyan app in the smartglasses, failed to respond to her inquiries Get our breaking news email , free app or daily news podcast The Australian privacy regul…
- BBC TechnologycommunityBraid-creator Jonathan Blow on making the 'biggest puzzle game ever'
Order of the Sinking Star is due out on Thursday and has roughly 1,500 puzzles for players to try
- AI Stack ExchangecommunityArduino photosensor led AI
I have a very basic circuit with 1 led connected to a digital pin, a photoresistor connected to a analog pin and im trying to teach the microcontroller when to light up the led. I have this code: #define readPin A1 #defi…
- TechCrunch AIstartupsEx-Ramp engineers raise $20M for platform Melius after scrapping their first product
Instead of helping marketers manage and optimize ad spend, the company is focusing on building the tools that generate the creative assets and campaigns.
- SiliconANGLE AIstartupsVinci reels in $250M for its engineering simulation platform
Vinci4D Inc. today announced that it has closed a $250 million funding round at a $1.5 billion valuation. Advent, Temasek and Xora jointly led the Series B deal. They were joined by several startup funds including AMD Ve…
- SiliconANGLE AIopen-sourceGoogle expands EmbeddingGemma beyond text to images, audio and video
Google LLC today released EmbeddingGemma 2, an open multimodal embedding model small enough to run on a smartphone. The release takes the EmbeddingGemma line beyond text, which was all the first version handled when Goog…