Agentic systems
5 mentions across all digests
Agentic systems are AI applications where language models autonomously plan actions and call tools to complete tasks, studied theoretically for foundations of agency and practically constrained by hardware limits on context window size.
To Throw a Stone with Six Birds: On Agents and Agenthood
arXiv paper rigorously defines what constitutes agents and agency from first principles—foundational work as agentic AI systems become mainstream.
Let's Have a Conversation: Designing and Evaluating LLM Agents for Interactive Optimization
Research identifies structured dialogue patterns that improve LLM agent design and evaluation for interactive optimization, establishing reusable blueprints for autonomous development tools.
[AINews] Context Drought
Improving instruction hierarchy in frontier LLMs
Keeping your data safe when an AI agent clicks a link