arXiv:2609.18481v1 Announce Type: new Abstract: Biomedical knowledge graphs combine ontology-derived hierarchies with transversal associations among…
First Token Matters: Understanding Safety Collapse in Large Reasoning Models
arXiv:2609.18471v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) exhibit strong problem-solving abilities, yet their safety alignment often…
Beyond Routine Compliance: Cunning Data Cultivates Safety Vigilance in Large Language Models
arXiv:2609.18515v1 Announce Type: new Abstract: Safety alignment teaches large language models (LLMs) to recognize harmful requests and reject risky…
Collective Loss of Control in LLM Agent Systems: An Epidemic Account of Mutation, Contagion, and Recovery
arXiv:2609.18460v1 Announce Type: new Abstract: How does a multi-agent system evolve from a local deviation into collective loss of control? We propose an…
The Mirage of Calibrated Confidence: Trajectory-Independence of Verbalized Confidence in Vision-Language Models
arXiv:2609.18453v1 Announce Type: new Abstract: A calibrated Vision-Language Model (VLM) can repeatedly self-correct, say “Wait, I should recheck,” arrive…
Cultural Competence in Context: A Large Language Model Passes the Turing Test in Finland
arXiv:2609.18394v1 Announce Type: new Abstract: We report the results of a Turing Test conducted in Finland in the Finnish language. Because languages and…
WetRobo: A Reproducible Robot Kit for Coding Agents in Biological Laboratories
arXiv:2609.18435v1 Announce Type: new Abstract: Automating biological research requires general-purpose, reproducible robot systems that allow individual…
HPOQuest: A Rare-Disease Diagnostic Agent Using Active Phenotype Acquisition
arXiv:2609.18431v1 Announce Type: new Abstract: More than 300 million people worldwide are affected by one of over 7,000 known rare diseases, yet…
We don’t need AI regulation — leave safety to us, Nvidia’s Jensen Huang says
AI isn’t some new form of “alien mind,” according to Jensen Huang. It’s just hardware and software, so safety can be engineered by each AI product maker.
Risk-Aware World Modeling with Flow-Guided Occupancy Evolution for Selective Trajectory Planning in Automated Driving
arXiv:2609.18442v1 Announce Type: new Abstract: Safe motion planning in automated driving requires anticipating evolving traffic risks and deciding when…
AI News Brief Hourly Summary 2026-09-17 11h : 11 posts
11 posts published in the last hour 08:32What Counts as Strategic Reasoning? A Systematic Mapping of Chess Research on Humans, Engines, and Language Models 08:32Market Signal Injection: Adversarial Context Manipulation of LLM Pricing Agents 08:32Visual Compliance via Executable Safety Rule…
What Counts as Strategic Reasoning? A Systematic Mapping of Chess Research on Humans, Engines, and Language Models
arXiv:2609.18286v1 Announce Type: new Abstract: Chess has long served as a model domain for studying search, expertise, decision-making, and artificial…
Market Signal Injection: Adversarial Context Manipulation of LLM Pricing Agents
arXiv:2609.18357v1 Announce Type: new Abstract: Large language model (LLM) pricing agents may respond to how market data is presented, even when its…
Visual Compliance via Executable Safety Rule Entailment
arXiv:2609.18328v1 Announce Type: new Abstract: Recent advances in LLMs and VLMs have enabled safety systems to reason beyond simple risk patterns toward…
Bad Genius: Counterfactual-Guided Harness Evolution Beyond Task-Specific Shortcuts
arXiv:2609.18366v1 Announce Type: new Abstract: Reliable agent evaluation is complicated by automatic harness optimization, which repeatedly uses a…
Faithful yet Collusive: Why Chain-of-Thought Monitoring Cannot Detect Collusion in LLM Pricing Agents under Oligopolistic Competition
arXiv:2609.18346v1 Announce Type: new Abstract: Large language models (LLM) deployed as autonomous pricing agents may sustain supracompetitive prices…
REPAIR: Resolving Long-Tail Confusion in Scientific Retrievers via Fact-Verified Iterative Refinement
arXiv:2609.18262v1 Announce Type: new Abstract: Precise retrieval of scientific information is fundamentally constrained by long-tailed concepts and high…
Who Audits Whom, on What Substrate, with What Evidence? An Independence-Graded Audit Protocol for Agentic AI
arXiv:2609.18272v1 Announce Type: new Abstract: Agentic AI systems plan, invoke tools and act with limited supervision; they are now both the subject of…