Skip to content

RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.

active 2025-03-182025-10-07 (UTC)

Partial coverage11,395 / 12,304 hourly files (93%) · 2 absent upstream · 906 failed, retryable2025-03-162026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
777
Pushes
57
Pull requests
26
Issues
39
Stars
541
Forks
58

Activity over time

Daily event counts in the loaded window

Line chart, 204 days from 2025-03-18 to 2025-10-07. Pushes: 57 total, peak 5 in a day. Pull requests: 26 total, peak 4 in a day. Issues: 39 total, peak 3 in a day. Comments: 44 total, peak 4 in a day. Stars: 541 total, peak 23 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

Recent activity

Latest issues, pull requests and releases

  • Pull request#133CryoLogicat2025-09-22 11:08
  • Issue comment#84pcj-sudo2025-09-18 03:04
    How to save generated trajectories (messages) in each validation round?
  • Issue comment#132qywMichelle2025-09-10 11:20
    warning about loss mask and response mask
  • Issue#132qywMichelle2025-09-09 12:29
    warning about loss mask and response mask
  • Pull request#131ZihanWang3142025-09-06 16:08
  • Issue#130WillDreamer2025-08-25 06:49
    Concerns on importance sampling
  • Issue#129zijianh42025-08-24 19:37
    Some questions about Webshop enviroment
  • Issue#121ChenBinfighting12025-08-18 07:15
    webshop parameters
  • Issue comment#121WillDreamer2025-08-17 02:16
    webshop parameters
  • Issue comment#124ZihanWang3142025-08-10 22:15
    self.actor_module in RAGEN/ragen/workers/actor/dp_actor.py
  • Pull request#126ZihanWang3142025-08-10 22:12
  • Pull request#126ZihanWang3142025-08-10 22:11
  • Issue comment#124Techie58792025-08-10 19:03
    self.actor_module in RAGEN/ragen/workers/actor/dp_actor.py
  • Issue comment#124Techie58792025-08-10 09:08
    self.actor_module in RAGEN/ragen/workers/actor/dp_actor.py
  • Issue comment#124jchy202025-08-10 02:08
    self.actor_module in RAGEN/ragen/workers/actor/dp_actor.py
  • Issue comment#124ZihanWang3142025-08-09 05:37
    self.actor_module in RAGEN/ragen/workers/actor/dp_actor.py
  • Issue comment#124jchy202025-08-08 18:47
    self.actor_module in RAGEN/ragen/workers/actor/dp_actor.py
  • Pull request#125ZihanWang3142025-08-08 16:46
  • Issue comment#124ZihanWang3142025-08-08 16:46
    self.actor_module in RAGEN/ragen/workers/actor/dp_actor.py
  • Pull request#125ZihanWang3142025-08-08 16:45
  • Issue#124jchy202025-08-08 04:36
    self.actor_module in RAGEN/ragen/workers/actor/dp_actor.py
  • Issue#122ZihanWang3142025-08-04 17:15
    Docs no longer active
  • Pull request#123ZihanWang3142025-08-04 17:15
  • Issue comment#82Kedaya662025-08-04 10:16
    RuntimeError: cannot reshape tensor of 0 elements into shape [0, -1] because the unspecified dimension size -1 can be any value and is ambiguous
  • Issue#122CakeCrusher2025-08-02 22:46
    Docs no longer active

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 541 stars here means stars gained during the window, not the repo's star count.