ZeroSlop — November 2, 2026
Today: Incongruence-Aware Evaluation of Multimodal Speech…; Agentic World Modeling for Agent Test-time Scaling…; Benchmarking Forecasting Agents on Yesterday's…
12 stories worth knowing about today — AI breakthroughs, launches, and innovations making a difference.
1. Incongruence-Aware Evaluation of Multimodal Speech Emotion Recognition in Audio Large Language Models
arXiv CS.AI
arXiv:2610.40883v1 Announce Type: new Abstract: Voice-interactive large language models process both what a speaker says and how they say it, yet the two channels do not always agree. We ask whether that disagreement degrades speech emotion recognition. Mapping text and audio into a shared valence-…
2. Agentic World Modeling for Agent Test-time Scaling without Environment Replica
arXiv CS.AI
arXiv:2610.40927v1 Announce Type: new Abstract: Test-time scaling (TTS) improves large language model agents by sampling and selecting among multiple candidate trajectories, but common realizations assume that these trajectories can be executed in parallel. This assumption breaks in realistic deplo…
3. Benchmarking Forecasting Agents on Yesterday’s Tomorrows
arXiv CS.AI
arXiv:2610.40940v1 Announce Type: new Abstract: Digital agents can now gather and organize information, reason over it, and use tools to complete complex tasks. Forecasting puts all of these abilities to the test: it requires integrating incomplete evidence, inferring causal drivers, and committing…
4. Capability-Grounded Agentic Planning
arXiv CS.AI
arXiv:2610.41040v1 Announce Type: new Abstract: LLM agents serve natural-language requests through tools, data sources, and other agents, and even simple requests often need several interdependent calls. Typically, the LLM picks these calls by trial and error, with no guarantee of an executable pla…
5. QUAL: Quantile Alignment Improves Zero-Shot Time-Series Foundation Models
arXiv CS.AI
arXiv:2610.41100v1 Announce Type: new Abstract: Time-series foundation models (TSFMs) provide zero-shot forecasts for unseen series, but their accuracy varies across datasets. Combining several models can reduce this variability, yet zero-shot deployment provides no target labels for selecting or w…
6. SystemD’s Creator Opens Signups for Private Preview of Amutable’s Cryptographically Verified Linux Systems
Slashdot
SystemD creator Lennart Poettering left Red Hat for Microsoft in 2022, but 10 months ago left to co-found Amutable a company that aims to build cryptographically verified Linux systems that stay trusted over time.
It’s FOSS calls it “a read-only, image-based system where every machine produces sig…
7. Amid AI Bans, Microsoft and OpenAI Plan a ‘Joyful’ Hour of AI for Kids
Slashdot
Generative AI was recently banned in America’s two largest school districts, just weeks after OpenAI launched ChatGPT for Teens.
But forging ahead, tech-backed nonprofit Code.org — now renamed CodeAI — has named OpenAI the “Lead Partner” for its 2026 Hour of AI (which last year replaced its signat…
8. Consensus Within, Competition Between: Decentralized LLM Teams for Perimeter Defense
arXiv CS.AI
arXiv:2610.41044v1 Announce Type: new Abstract: The use of large language models (LLMs) to coordinate multi-agent teams raises a fundamental architectural question: whether task allocation should be centralized in a single LLM controller or distributed across autonomous LLM agents, particularly whe…
9. Opening the Box Changes the Cat: LLMs Detect Chain-of-Thought Monitoring - What now?
arXiv CS.AI
arXiv:2610.40946v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning allows large language models (LLMs) to generate intermediate reasoning traces in natural language while solving complex tasks. These traces can support safety monitoring by exposing potentially harmful plans before act…
10. National Grid to site biggest substation in UK near planned Teesside datacentre
The Guardian Tech
New electricity generating capacity would enable north-east to attract investment for large-scale AI infrastructure National Grid has taken a step towards building Britain’s biggest electricity substation on Teesside, which could supply power to a vast neighbouring datacentre as the UK races to expa…
11. NVIDIA Releases Auto Ontology: An Open Semantic Layer That Grounds AI Agent SQL
MarkTechPost
NVIDIA released Auto Ontology, an Apache 2.0 library that generates a semantic layer from enterprise metadata. It grounds agent SQL in certified definitions and serves context through MCP, CLI and API. The post NVIDIA Releases Auto Ontology: An Open Semantic Layer That Grounds AI Agent SQL appeared …
12. ChatGPT as a Surveillance Assistant? An Exploratory Case Study of AI-Assisted Surveillance Risks
arXiv CS.AI
arXiv:2610.40890v1 Announce Type: new Abstract: Large language models (LLMs) can generate detailed guidance, functional code, and persuasive text at scale. As one of the most widely used consumer language model products as of 2026, ChatGPT gives broad public access to these capabilities, motivating…