· ai
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 trai...
Source
Amazon Science
9 posts from this source
-
- · software
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 ex...
- · ai
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....
- · software
The 10 most viewed publications of 2025
From foundation model safety frameworks and formal verification at cloud scale to advanced robotics and multimodal AI reasoning, these are the most viewed publi...
- · software
The 10 most viewed blog posts of 2025
From quantum computing breakthroughs and foundation models for robotics to the evolution of Amazon Aurora and advances in agentic AI, these are the posts that c...
- · software
Dialogue Boost: How Amazon is using AI to enhance TV and movie dialogue
New audio-processing technology is making entertainment more accessible for millions of viewers....
- · ai
Amazon Nova Forge: "Open training” paradigm that empowers everyone to build their own frontier AI
New service lets customers mix their own data with the data used to train Amazon Nova at each major stage of model development, enabling deep domain understandi...
- · ai
AutoGluon assistant: Zero-code AutoML through multiagent collaboration
A multiagent architecture separates data perception, tool knowledge, execution history, and code generation, enabling ML automation that works with messy, real-...
- · ai
AI-native 6G: From networks to intelligence fabrics
“Network language models” will coordinate complex interactions among intelligent components, computational infrastructure, access points, data centers, and more...