Meet LangChain’s DeepAgents Library and a Practical Example to See How DeepAgents Actually Work in Action

APTBench: Benchmarking Agentic Potential of Base LLMs During Pre-Training

Crucible: Quantifying the Potential of Control Algorithms through LLM Agents

Anthropic AI Releases Petri: An Open-Source Framework for Automated Auditing by Using AI Agents to Test the Behaviors of Target Models on Diverse Scenarios

I think "agent" may finally have a widely enough agreed upon definition to be useful jargon now

LangChain for EDA: Build a CSV Sanity-Check Agent in Python

CoreThink: A Symbolic Reasoning Layer to reason over Long Horizon Tasks with LLMs