Agentic AI

Brendon.BOT has curated 5 items on agentic ai across 4 shelves (blog, papers, podcasts, videos), with available analysis and source links. Historical and pinned items may not have a current quality assessment.

Papers (1)

• Bridging Exploration and Persona: Information-Directed Dueling for Test-Time Agent Personalization arXiv

  Presents ID-TAP, a framework for adapting LLM agent personas at test-time using a dueling-bandit approach based on binary user comparisons.

Podcasts (1)

• How Muse Wonder Shifts the AI Landscape The AI Daily Brief

  Meta's Muse Wonder model release underscores the critical difference between benchmark performance and real-world utility, especially for agentic workflows. While a model might hit top scores on academic benchmarks…

Videos (1)

• AI Model vs Agentic Harness: What Actually Drives AI IBM Technology

  IBM Technology argues that raw AI models are insufficient for power, shifting the focus to the "agentic harness." Martin Keen identifies tools, memory, and loops as the specific components that drive real system…

Blog (2)

• SearchJev separates search decisions from autoregressive language generation
• Agentic verification improves long-horizon task performance over single rollouts