The AI knowledge 99.9% of people never discover
New DFKI preprint argues AI in pre-demolition audits must prioritise defensible decisions over accuracy, proposing four knowledge-graph modes.
TrustX ARC, a new arXiv preprint, scores agentic AI risk across 12 dimensions into three governance tiers for risk officers, developers and regulators.
A new arXiv preprint pairs an LLM planner with a forecasting model to guard industrial control systems, recording zero hallucinated actions in attack
KV-PRM reads the memory AI models already produce during generation, slashing the cost of verifying multi-agent reasoning chains by up to 5,000x.
New arXiv paper with 489 probes shows structural scaffolding around a fixed LLM cuts failure rates, challenging the bigger-model assumption.
A new arXiv paper from July 2026 unveils a four-agent system that decomposes abstract reasoning puzzles into perception, code search, and reflective
A new 86-case benchmark finds Codex and Claude Code agents violate logical constraints in skill files up to 70% of the time, causing privacy leaks and
New arXiv preprint proposes auction-based routing for LLM agents, sending reasoning steps to the most capable solver rather than the most overconfident.
A preprint shows backdoors in feedforward neural networks evade every statistical test, even with full access to all weights, breaking model trust.
