ZeroSlop — September 10, 2026
Today: Do Agents Know When They Succeed? Calibrating Agent…; Multi-Agent Agentic Graph Learning via Structural…; Anthropic Reveals Fourth Likely Crime Committed By Its…
12 stories worth knowing about today — AI breakthroughs, launches, and innovations making a difference.
1. Do Agents Know When They Succeed? Calibrating Agent Confidence from Internal Representations
arXiv CS.AI
arXiv:2609.09448v1 Announce Type: new Abstract: As agentic systems getting adopted rapidly in safety critical applications, it is vital to measure the confidence associated with the agentic actions. In comparison to the traditional machine learning systems, agentic workflows have complex failure mo…
2. Multi-Agent Agentic Graph Learning via Structural Signatures
arXiv CS.AI
arXiv:2609.09565v1 Announce Type: new Abstract: Agentic graph learning (AGL) has recently achieved promising results on graph reasoning tasks, where an agent powered by a large language model (LLM) sequentially samples the graph as evidence to support its final prediction. Existing methods either e…
3. Anthropic Reveals Fourth Likely Crime Committed By Its AI
Slashdot
An anonymous reader quotes a report from The Register: Amid industry soul-searching about the possibility of AI improving itself to the point that it kills everyone, Anthropic has revealed yet another incident that would qualify as a crime if perpetrated by a person. The AI biz published “an alignme…
4. An Autonomous GeoAI Agent for Arctic Eco-Navigation
arXiv CS.AI
arXiv:2609.09374v1 Announce Type: new Abstract: Arctic maritime navigation is becoming increasingly important as changing sea-ice conditions expand seasonal accessibility while simultaneously introducing substantial operational, environmental, and community risks. Arctic route planning is inherentl…
5. PRAGMA: Evaluating Personalized Guidance with Memory Alignment in Lifelong Conversations
arXiv CS.AI
arXiv:2609.09664v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as personalized assistants that interact with users over extended periods of time. As conversations grow longer, relying on full interaction histories becomes increasingly inefficient and unreliab…
6. Can Artificial Intelligence Support Healthcare and Mental Health Through Early Cyberbullying Detection ? The Impact of Emotion-Aware AI on Proactive Online Safety
arXiv CS.AI
arXiv:2609.09735v1 Announce Type: new Abstract: Healthcare systems, mental health, and public well-being are increasingly affected by cyberbullying and harmful online interactions. This paper presents CareGuard, an early-warning framework designed to support healthcare-driven mental health protecti…
7. OpenAI adds a prominent AI doomer to its board of directors
TechCrunch AI
Paul Christiano, an influential AI researcher focused on alignment, is joining the OpenAI Foundation as a member of its board….
8. More than 10% chance AI ‘could kill all humans’ in the next 10 years, Anthropic safety researcher says — departing employee says AI companies are ‘gambling with our lives’
Tom’s Hardware
Anthropic AI safety researcher has warned there’s a more than 10% chance AI could kill all humans….
9. OpenAI Says It Has Cracked One of Math’s ‘Millennium Problems’
Slashdot
An anonymous reader quotes a report from The New York Times: OpenAIsaid on Tuesday that its newest artificial intelligence technology had solved one of the “Millennium Problems,” a collection of important unanswered math questions meant to push the world’s leading mathematicians to new heights. The …
10. ICYMI: What landed for AI builders in August 2026
AWS Machine Learning
A recap of August 2026 launches for AI builders across Amazon Bedrock, Amazon Bedrock AgentCore, and Strands: million-token context for OpenAI models, cross-Region inference, agents that run for up to 14 days on dedicated compute, expanded AWS GovCloud availability, and Strands Robots for physical d…
11. Black-Box Red Teaming of Agentic AI: A Taxonomy-Driven Framework for Automated Risk Discovery
arXiv CS.AI
arXiv:2609.09647v1 Announce Type: new Abstract: Agentic systems are rapidly moving to production, where they read untrusted inputs, call tools with real permissions, and act autonomously, expanding the security surface beyond chat-only models. Yet standard evaluations remain single-turn and fail to…
12. On the Navier–Stokes Millennium Prize Problem
Simon Willison
On the Navier–Stokes Millennium Prize Problem Impressive result from OpenAI, who used an unreleased model to produce a resolution to the Navier–Stokes existence and smoothness problem , one of the seven Millennium Prize Problems that have been subject to a $1,000,000 prize since May 24th, 2000. The …