Repository navigation
Conversation
ShubyM
force-pushed
the
blog/harvey-lab-recipe
branch
from
November 6, 2026 18:37
eb1dfbe to
cc5f761
Compare
ShubyM
marked this pull request as ready for review
November 6, 2026 18:55
ShubyM
force-pushed
the
blog/harvey-lab-recipe
branch
3 times, most recently
from
November 7, 2026 01:02
f02e9f9 to
4807e7f
Compare
Adds the draft post 'Post-Training Open-Weight Models on Legal Tasks with OpenRL' under site/content/blog/post-training-legal-agents/ along with its architecture and evaluation SVGs. Signed-off-by: Shuby Mishra <shuby@google.com>
ShubyM
force-pushed
the
blog/harvey-lab-recipe
branch
from
November 7, 2026 01:16
4807e7f to
7cf65e8
Compare
droot
approved these changes
Nov 7, 2026
This branch has not been deployed
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds the draft engineering blog post "Post-Training Legal Agents on OpenRL" (
site/content/blog/post-training-legal-agents/) along with its SVG architecture diagram and evaluation charts:index.md(draft: true): covers connecting Harvey's Legal Agent Benchmark to OpenRL's Tinker-compatible API, full-context training with the Automodel backend, prefix-awarellm-drouting and sandbox integration, and RL / SFT + RL evaluation results on Gemma 4 and Qwen 3.5.harvey-architecture.svg,gemma-e4b.svg,backends.svg,quality.svg: inline Figtree-embedded SVG figures matching the site's visual style.