Skip to content
Eval Suites50

DeepSWE (Agentica)

An open RL-trained coding agent, not a benchmark. Its release reports results on SWE-bench Verified with test-based verifiers; listed here for its reproducible evaluation setup.

DeepSWE (Agentica) at a glance

Maintainer
Agentica; Together AI
Size
Model, not a dataset[1]
Category
Coding & Systems
Runs with
R2E-Gym
License
Not stated by the source. Check before commercial use.
Tier
frontier

Failure modes DeepSWE (Agentica) catches

Overfitting to verifiers
Patch errors

Starter command

A starting point, not a guarantee. Commands change between releases, so confirm against the official README.

DeepSWE (Agentica) starter
git clone https://github.com/agentica-project/R2E-Gym
# follow the repo README for setup and run commands

Sources

  1. 1. DeepSWE (Agentica) official page or repository · Agentica; Together AI · Repository · Sources checked