I've been reading BEACON from Zhejiang University's ZJU-REAL lab (arXiv:2605.06078), and the more I...
I've been reading BEACON from Zhejiang University's ZJU-REAL lab (arXiv:2605.06078), and the more I read it the more directly applicable it felt to the long-horizon agent work we're doing. So I'm turning that into a series.
The framing
To build a long-horizon agent that actually works, I think two things have to be right:
1. The agent keeps making progress toward the goal
Context compaction — what is safe to forget
Been heads-down lately, but I finally had a couple of days to catch up on some recent papers. Sharing...
Give a capable coding agent a real, multi-week project and watch what breaks. It isn't intelligence....
Where your agent runs and where it runs code are two different questions. Answer them separately.
You don't need a better agent. You need a better debug loop. I've been building agentic systems long...
Here is the uncomfortable thing I have landed on after a year of watching coding agents succeed and...
Your agent prints a sentence a human reads. To build on it — a UI, an eval, an API — you need data. This post makes the final…
