Great paper from Google on building benchmarks for data agents.
Static data-agent benchmarks saturate quickly and can't target a specific skill.
SynthCorp generates the data instead. It simulates routine business events and disruptions on a virtual calendar, and those events
// Trustworthy Recursive Self-Improvement //
Self-improving agents usually keep any harness update that raises the validation score, so noisy gains get accepted, and this later costs performance.
Researchers measured how often this happens. Under a greedy gate, 45.59% of
Recursive self-improvement is one of the most discussed ideas in AI right now.
Banger paper on RSI for frontier pre-training.
They claim to be the first in the world to apply RSI to an entire frontier pre-training run from scratch.
This work uses agent-driven loops on a single
Interesting insights about agent memory.
Might be worth a read if you are building memory systems for your agents.
Can an agent's memory make it fail tasks it would solve without memory?
KAIST researchers find that it can, and they call it memory-induced degradation.
The
Great practical paper on optimizing harness costs.
For lower agent costs, you want to change the harness and keep the model.
UC Berkeley researchers found that harness changes such as prompts and tools barely move accuracy, but they change cost by up to 2.6x on the same model