Amazon Science
@amazon.science
Reinforcement learning boosts AI agent task success two- to fourfold with small training sets. AWS research shows smaller models can match larger proprietary models at 1% to 2% the cost.
Customizing multiturn AI agents with reinforcement learning
Leveraging existing environment simulators and reward functions based on verifiable ground truth boosts task success rate, even with small models and small training datasets.
www.amazon.science
January 15, 2026 at 6:27 PM
Reinforcement learning boosts AI agent task success two- to fourfold with small training sets. AWS research shows smaller models can match larger proprietary models at 1% to 2% the cost.
SharpZO enables edge AI fine-tuning using only forward passes. The approach achieves 7% higher accuracy than existing low-memory methods and converges in as little as one-tenth the time: https://amzn.to/4pLQek8
Fine-tuning vision-language models on memory-constrained devices
A new hybrid optimization approach allows edge devices to fine-tune vision-language models using only forward passes, achieving up to 7% higher accuracy than existing techniques.
www.amazon.science
January 12, 2026 at 8:33 PM
SharpZO enables edge AI fine-tuning using only forward passes. The approach achieves 7% higher accuracy than existing low-memory methods and converges in as little as one-tenth the time: https://amzn.to/4pLQek8
Reposted by Amazon Science
No data, no AI, no progress. My @AmazonScience article explores how multi-layered mapping + petabyte-scale cloud infrastructure helps save lives in time of crisis. Building AI without addressing the fundamental data divide means solving the wrong problems. amazon.science/blog/why-ai-...
Why AI for good depends on good data
New technologies are helping vulnerable communities produce maps that integrate topographical, infrastructural, seasonal, and real-time data — an essential tool for many humanitarian endeavors.
amazon.science
October 14, 2025 at 2:02 PM
No data, no AI, no progress. My @AmazonScience article explores how multi-layered mapping + petabyte-scale cloud infrastructure helps save lives in time of crisis. Building AI without addressing the fundamental data divide means solving the wrong problems. amazon.science/blog/why-ai-...
"Normcore agents" are trained by Amazon's AGI Lab to chain together hundreds of micro-interactions to execute customer requests. In reinforcement learning gyms, agents practice atomic behaviors across dozens of application domains, learning to execute complex workflows with near-perfect reliability:
The unseen work of building reliable AI agents
"Reinforcement learning gyms" train agents on the many low-level tasks that they must chain together to execute customer requests.
www.amazon.science
January 8, 2026 at 5:27 PM
"Normcore agents" are trained by Amazon's AGI Lab to chain together hundreds of micro-interactions to execute customer requests. In reinforcement learning gyms, agents practice atomic behaviors across dozens of application domains, learning to execute complex workflows with near-perfect reliability: