🏷️ Posts Tagged "#Agent orchestration"

image of a robot in a small messy office labeled 200k tokens with lots of papers flying around; second image of robot with swirly eyes in a larger messy office labeled 1M tokens
📅

Context, optimized - The next season of agents (Part 3)

A breakthrough in parallelization depends on efficiently orchestrating long-running loops and short-running tasks, using the new tools discussed in part 2. What is the main challenge as we push these limits? The biggest issue with long-running loops today is context collapse, which invariably occurs when something goes off track in the agentic workflow. Even when everything works as intended, LLMs still struggle, with a decline in the LLM's attention and intent detection often attributed to context rot.
Read Post
image of a agent robot in a school environment showing students how to juggle tomatoes; followed by a second image showing them try to juggle tomatoes but dropping them on stage
📅

The next season of agents (Part 2) - Parallelization, from Ralph loops to science

So much can change in one year, and even more in just six months. The season of agents is now in full swing, and no one is building for chat anymore. In this post, we'll discuss parallelization - what current capabilities exist and what may come next. None of the predictions mentioned here are inevitable, and each will require significant effort to materialize, some may never pan out. However, if they all stack together, it can spell the beginning of a whole new season of agents.
Read Post