xiaohei/model_garden
1
0
Fork 0
mirror of https://github.com/GoogleCloudPlatform/vertex-ai-samples.git synced 2026-09-26 14:42:04 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
936a6adf775c04e92d365d5900e49580170b575d
model_garden/docs/vertex-training-cluster/images_tau2/rl_tau2_architecture.png
T
genquan9andGitHub 936a6adf77 Add multi-turn RL for tau2-bench technical report (#4558) 
* Add multi-turn RL for tau2-bench technical report

Add technical report documenting multi-turn reinforcement learning
training pipeline for tau2-bench customer service benchmark, including
GRPO training, data synthesis pipeline, and evaluation results.

* Fix deprecated MathJax CDN and broken anchor link

- Remove deprecated cdn.mathjax.org script tag (GitHub renders LaTeX natively)
- Fix broken ToC anchor from #2-bench to #tau2-bench
2026-08-05 16:25:05 +00:00

300 KiB
1382x1202px
Raw History

/xiaohei/model_garden/raw/commit/936a6adf775c04e92d365d5900e49580170b575d/docs/vertex-training-cluster/images_tau2/rl_tau2_architecture.png
Reference in New Issue View Git Blame Copy Permalink