https://ruisun33.github.io/posts/ad-arena/ 2026-02-27T06:41:41+00:00 https://ruisun33.github.io/posts/dynamic-context-control/ 2026-02-27T06:41:41+00:00 https://ruisun33.github.io/posts/geometry-of-learnable-reward/ 2026-02-27T06:34:21+00:00 https://ruisun33.github.io/posts/trace-bench/ 2026-02-27T06:41:41+00:00 https://ruisun33.github.io/categories/ 2026-07-07T01:12:46+00:00 https://ruisun33.github.io/projects/ 2026-07-07T01:12:46+00:00 https://ruisun33.github.io/tags/ 2026-07-07T01:12:46+00:00 https://ruisun33.github.io/archives/ 2026-07-07T01:12:46+00:00 https://ruisun33.github.io/about/ 2026-07-07T01:12:46+00:00 https://ruisun33.github.io/ https://ruisun33.github.io/tags/benchmark/ https://ruisun33.github.io/tags/simulation/ https://ruisun33.github.io/tags/advertising/ https://ruisun33.github.io/tags/context-management/ https://ruisun33.github.io/tags/thompson-sampling/ https://ruisun33.github.io/tags/test-time-optimization/ https://ruisun33.github.io/tags/reinforcement-learning/ https://ruisun33.github.io/tags/reward-hacking/ https://ruisun33.github.io/tags/rlvr/ https://ruisun33.github.io/tags/agentic-ai/ https://ruisun33.github.io/categories/projects/ https://ruisun33.github.io/categories/thoughts/