What changes when AI can plan, use tools and act? Explore research on autonomous workflows, multi-agent coordination and recovery from mistakes, with practical guidance for teams deciding what to automate and how to evaluate it.
What makes an LLM agent different from a chatbot? Understand tools, feedback, revision and the limits of autonomous workflows.
Why office AI agents lose context across turns, what the research tests, and how to evaluate tool arguments, meeting updates and recovery.
How SagaLLM proposes to preserve state, validate plans and recover from failures—and what its planning experiments establish about dependable AI agents.
Understand ODI’s conceptual framework and turn agent coordination into explicit state, approval, recovery and evaluation requirements.
MacNet tests how AI agent team size and network structure affect quality. Learn the scaling limits, merge risks and a practical evaluation approach.
SPIN-Bench separates legal actions, completed plans and agent coordination. Use its findings to design stronger tests for AI workflows.
How LLMs collect preferences and revise team decisions. Explore the original meeting example, simulation results and the limits of automated consensus.
A practical reading of AI-agent architecture: perception, memory, tools and outcome checks. Learn when a stateful workflow needs more autonomy.
