Evaluating Large Language Models for Travel Planning Tasks
Explore how large language models perform in travel planning, highlighting strengths and key limitations in reasoning and error correction.
Improving Agent Safety with ROME and ARISE Benchmarks
Discover how ROME and ARISE enhance AI agent safety judgment in deceptive scenarios using advanced benchmarks and analogical reasoning.
Cotomi Act: AI Automation Learning from User Behavior
Discover how Cotomi Act uses AI to automate tasks by observing user behavior, boosting productivity and enhancing organizational knowledge.
Deterministic Computation in LLMs: Prompting vs Execution
Explore how prompting and execution-based methods impact deterministic computation accuracy in large language models (LLMs).
ADAPTS: Automated Protocol-Agnostic Symptom Tracking
Discover ADAPTS, a novel framework for automated, protocol-agnostic tracking of depression and anxiety symptoms with expert-level accuracy.