Diffbrief Engineering daily

← Friday, October 2, 2026AgentsPaper

GraphForge grounds agent tasks and verifiers in real workspace files

huggingface.co by Qisheng Su et al. Editor score 8/10

GraphForge builds evidence graphs from real files to generate verifiable tasks, then uses a rollout and revision agent to check them; fine-tuning Qwen3.6-27B on 2,169 trajectories raises GDPVal by 65.7 under OpenHands. This offers a concrete data-generation approach for training work agents.

What
GraphForge synthesizes working-agent tasks and verifiers grounded in real workspace files through an evidence graph.
Method
It assembles files, derives task statements and rubrics from the graph, tests executability in an initial rollout, and uses a revision agent to repair them.
Why it matters
The pipeline provides a way to train agents on diverse file-based tasks with requirements and verification criteria anchored to source files.
assembles builds relati… derives tests repairs occupation-grou…seeds workspace ofreal files evidence graph task statementand rubrics initial rollout revision agent
GraphForge builds file-grounded tasks and revises them after an initial executability test. Sketched from the article's own text.

Read on huggingface.co →

Discussion

Discussion is not switched on yet. Use Note above to keep your own thoughts on this story.

Headline, summary, brief and diagram are written by a model from the source's own text; the link, byline and numbers come from the source. Read the original before relying on a claim.

Your note

Private to you. Stored in this browser, and synced to your account when you are signed in.