What should an agent keep from a failed attempt?
Reflexion gives an agent written feedback to carry into its next attempt. I'm interested in what makes that feedback useful enough to keep.
Read
Research
Papers that caught my attention and what I'd like to learn from them.
The system around the model deserves its own tests
A paper on natural language agent harnesses raises a question I care about: can we check how the workflow runs, not just whether we like the final answer?
What WikiSkill suggests for my research wiki
An agent's history, the lessons we keep and the skills it uses are different things. WikiSkill gives me a useful way to think about connecting them.