15 posts published in the last hour
- 05:32FraudBench: Stress-Testing Policy-Grounded Banking Agents Against Adaptive Fraud
- 05:32Looped Language Models Improve Compositional Tool Calling
- 05:32Amazon Bedrock AgentCore payments is now generally available: Enabling agents to transact safely and autonomously at scale
- 05:32Adversarial Review: Structured Disagreement for Grounded Agentic Code Review
- 05:32OpenAI says it’s “pacing model development” as AI cybersecurity risks grow too dangerous
- 05:32RDFdL: Integrating RDF with Differential Dynamic Logic
- 05:32Pacing model development in an era of cyber-critical capabilities
- 05:32Efficient Adaptation of LLMs for Hate Speech Detection in Low-Resource Languages: A Comparative Study on Roman Urdu
- 05:03Solving Is Not Drawing: A Benchmark for Diagrammatic Reasoning in Olympiad Geometry
- 05:03Improving Rural Medication Safety with AI: A Scoping Review
- 05:03Position: AI Leaderboards Are Underserving the Global South: A Case Study from India
- 05:03How Much Memory Does Your Agent Actually Need?
- 05:03Safety Alignment Illusion: The Cross-Lingual Safety Gap in LLMs
- 05:03New benchmark ranks search APIs for AI agents on quality, cost, and speed
- 05:03Optimized Fuzzy Logic Approach with the IEEE Key Gas Method for Diagnosing Power Transformer Faults Using Dissolved Gas Analysis
