News

AI Provider Index news.

Updates, product notes and practical coverage for AI platforms and operators.

#ReinforcementLearning
Open Hugging Face shows harness-specific adapters can make coding agents leaner and more accurate · Ronald

Hugging Face shows harness-specific adapters can make coding agents leaner and more accurate

Hugging Face has published a reproducible reinforcement-learning recipe for adapting Qwen3.8-27B to specific coding-agent harnesses. Specialist LoRA adapters improved benchmark accuracy while cutting tool calls and generated tokens, and a merged super-adapter transferred gains across three harnesses. The results highlight deployment context as a trainable part of agent performance.

Open SageMaker multi-turn reinforcement learning lifts Wordle solve rates · Ronald

SageMaker multi-turn reinforcement learning lifts Wordle solve rates

AWS has published an end-to-end SageMaker AI multi-turn reinforcement learning guide using a Wordle agent hosted on Bedrock AgentCore. The example trains GPT-OSS-20B from episode-level rewards, lifting held-out solve rates from 61 to 84 per cent at serving settings while documenting reward design, validation differences, token costs and deployment requirements.