Morph MORPH
SIGN IN SIGN UP
dhruvhead / slime UNCLAIMED
0 0 1 Python

COMMITS

/ examples/coding_agent_rl/README.md
docker
June 17, 2026
J
[coding-agent-rl] Refactor coding-agent RL: turn-node TrajectoryManager + pluggable harness layer (#2005)
jingshenghang committed
243773c
June 4, 2026
Z
Revert "rename rollout_ids to group_ids" (#2013)
Zilin Zhu committed
44d29ee
May 30, 2026
Z
rename rollout_ids to group_ids (#1984)
Zilin Zhu committed
a3c5462
May 29, 2026
Z
[agent] Fix dropping overlong sample (#1982)
Zilin Zhu committed
cc50ea5
Z
[agent] extract Adapter class (#1981)
Zilin Zhu committed
41c94f4
Z
[agent] Add openai and anthropic adapters (#1979)
Zilin Zhu committed
acac661
Z
[docs] Add finer explanation for re-tokenizationi issue (#1974)
Zilin Zhu committed
c01b647
May 27, 2026
Z
Fix trajectory merging logic (#1963)
Zilin Zhu committed
afc323f
Z
Extract more util code from coding_agent_rl example (#1960)
Zilin Zhu committed
ad3b874
Z
Minor refactor for coding agent rl logic and remove SWE_LIST_TRAJECTORY (#1957)
Zilin Zhu committed
e239113
Z
Add slime/agent/ and move sandbox impl inside (#1956)
Zilin Zhu committed
d84dad7
May 26, 2026
J
[examples] add coding_agent_rl: agent-in-sandbox RL minimal demo (#1923)
jingshenghang committed
b676413