BarryC ffb9491c47 feat: [AutoRL-Bench] Update DeepSearchQA split and translate task instructions to English (#1368) ...

* fix(alfworld): stop exposing react prompts to agents

* fix(deepsearchqa): use deterministic 100/800 split

* fix(deepsearchqa): switch default split to 100/200

* docs(autorl-bench): translate task instructions to english

2026-03-19 20:44:46 +08:00

..

alfworld

feat(rl): add AutoRL-Bench framework and benchmark integrations (#1348)

2026-03-17 15:49:30 +08:00

alpacaeval

feat(rl): add AutoRL-Bench framework and benchmark integrations (#1348)

2026-03-17 15:49:30 +08:00

deepsearchqa

feat: [AutoRL-Bench] Update DeepSearchQA split and translate task instructions to English (#1368)

2026-03-19 20:44:46 +08:00

gsm8k

feat(rl): add AutoRL-Bench framework and benchmark integrations (#1348)

2026-03-17 15:49:30 +08:00

humaneval

feat(rl): add AutoRL-Bench framework and benchmark integrations (#1348)

2026-03-17 15:49:30 +08:00

smith

feat(rl): add AutoRL-Bench framework and benchmark integrations (#1348)

2026-03-17 15:49:30 +08:00

webshop

feat(rl): add AutoRL-Bench framework and benchmark integrations (#1348)

2026-03-17 15:49:30 +08:00

__init__.py

feat: [AutoRL-Bench] Update DeepSearchQA split and translate task instructions to English (#1368)

2026-03-19 20:44:46 +08:00