The Thinking Notes

HOME
CATEGORIES
PROJECTS
TAGS
ARCHIVES
ABOUT

Home Categories

Categories

Categories

Projects 3 posts

Thoughts 1 post

Recently Updated

Ad Arena
Dynamic Context Management
Trace-Bench
The Geometry of Learnable Reward

Trending Tags

benchmark reinforcement-learning advertising agentic-ai context-management reward-hacking RLVR simulation test-time-optimization thompson-sampling

© 2026 R S. Some rights reserved.

Using the Chirpy theme for Jekyll.

Trending Tags

benchmark reinforcement-learning advertising agentic-ai context-management reward-hacking RLVR simulation test-time-optimization thompson-sampling

New content available