Banger paper from Google on RSI.
(bookmark it)
They propose an approach for continual recursive self-improvement at the harness level. They also propose their own self-improving memory system for the harness optimizer.
This clearly highlights the importance of traces and having a functional, adaptive, and structured persistent memory system in your harness.
They show that a harness optimizer improves 9 of 10 continued runs when it remembers why it made each past edit.
They discuss that a common problem shows up when you change the model or the benchmark. An Opus-evolved harness started at 68.41 on Gemini, below the 73.89 of the plain seed harness.
Self-Improvement Memory groups past edits by the harness problem they addressed. For each edit, it stores the rationale, predicted outcome, observed outcome, and evaluation context. The proposer and the selector both read it before making new changes.
Across four domains, including Terminal-Bench 2.1 to Terminal-Bench 4, SIM beats continuing from the harness alone in six cross-dataset and four Opus-to-Gemini settings. Across ten coding runs, it adds 2.36 points on average (p=0.003).
If you evolve harnesses automatically, store the reasons and results of each edit next to the code.
https://t.co/VvUfmVFC3H
Chat with Paper: https://t.co/DcEJoYBDba
🚀 Introducing DeepInfer, our in-house inference framework, now fully open source!
Powering DeepSeek-V4.1-Flash at scale with high throughput and low latency. We’re sharing our production stack to help the community lower compute costs, reduce energy use, and make AI more affordable.
🔗 https://t.co/JGAik1kgk0
1/4
I'm joining OpenAI next week!🥹 The job search turned out to be really challenging but also super rewarding, so I wrote a small blog to share what I learned along the way and hopefully make the process a little less mysterious for the next person. https://t.co/6FigSBdenD
Our 🔭VISTA🔭 paper is now on arXiv, with more ablations and results!
We introduced VISTA in our Aug 5 blog post. The paper further evaluates it on visual games and reasoning tasks beyond ARC-AGI-3 🧵
Paper: https://t.co/l9a746yjpt
Code: https://t.co/DsJBFmjUEy
Previous blog post: https://t.co/bYUWwi0KoQ