arXiv:2609.07075v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) is commonly evaluated by whether the final answer is correct. That…
Tag: AI
Risk Is Not Review Value: Wrong-Answer Exposure Under Bounded Review Budgets
arXiv:2609.07095v1 Announce Type: new Abstract: LLM assistants often produce more answers than humans can review before users see them. Most evaluations…
VST: Verifiable Structured Transport for Auditable Agent-to-Agent Alpha Discovery
arXiv:2609.07065v1 Announce Type: new Abstract: Agent-to-agent (A2A) alpha discovery is slowed by repeated feedback cycles between mining and evaluation…
Task-Aligned vs. Human-Aligned: Why AI’s Next Benchmark Should Be Us
Every few months, a new model arrives and shuffles the AI leaderboards. According to Stanford’s 2026 AI Index Report, frontier models gained roughly 30…
EEG-Driven Decoding Framework for Passenger Hazard Perception in Highly Automated Vehicles
arXiv:2609.07128v1 Announce Type: new Abstract: Reliable risk assessment remains a central challenge for Autonomous Vehicles (AVs). Despite advances in…
AI Is Not Taking Our Jobs. But Energy Costs Might.
The AI jobs panic isn’t backed by the numbers. The AI energy problem is real, and it’s now a question of whether Britain can build and deploy fast enough…
Beyond Sparse Rewards: A New Benchmark and Structure-Aware Graph Alignment for Micro-Drama Understanding
arXiv:2609.07107v1 Announce Type: new Abstract: Micro-dramas, characterized by ultra-short durations and hyper-dense storylines, pose unique challenges…
Beyond One-Shot Expansion: Contrastive Evidence Exploration for Multi-Hop Retrieval
arXiv:2609.07050v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) critically depends on retrieving the evidence necessary for effective…
When and Why LLM Causal Priors Help: Closed-Loop Prior Selection for Amortized Causal Inference
arXiv:2609.06941v1 Announce Type: new Abstract: Causal effect estimation asks how an outcome would change under an intervention, and medicine, economics,…
Powering AI is an architecture problem
On July 22, 2026, a transmission line fault in Ashburn, Virginia—the heart of the world’s largest data center cluster—knocked more than 3 gigawatts of…