Roland Minrui 5594ab418b fix: refine DSCoSTEER_eval prompts (#1157) ...

* change DSCoSTEER_eval prompts

* fallback to better exp only

* fix fallback

* fix and reformat

* fix bug when base_fb is None

* add reasoning to hyperparameter evaluation

* feat: add acceptable assessment in exp_feedback (#1159)

* add time

* refine eval prompt and make the logic of tuning check more clear

* some refinement

* fix CI

* fix a small bug, only consider score in runner

* refine comment

* simplify compare function

---------

Co-authored-by: jingyuanlm <842442862@qq.com>
Co-authored-by: Xu <v-xuminrui@microsoft.com>
Co-authored-by: Jensen Lee <91518020+Jensen246@users.noreply.github.com>
Co-authored-by: Xu Yang <peteryang@vip.qq.com>

2025-08-06 22:55:25 +08:00

..

conf.py

feat: enable finetune llm (#1055)

2025-08-06 12:24:44 +08:00

developer.py

refactor: refactor core framework to better propogate feedbacks (#599)

2025-02-16 01:40:44 +08:00

evaluation.py

feat: fallback to acceptable results (#1129)

2025-07-31 17:53:18 +08:00

evolving_agent.py

feat: fallback to acceptable results (#1129)

2025-07-31 17:53:18 +08:00

evolving_framework.py

feat: fallback to acceptable results (#1129)

2025-07-31 17:53:18 +08:00

exception.py

feat: enhance timeout handling in CoSTEER and DataScience scenarios (#1150)

2025-08-04 17:44:51 +08:00

experiment.py

feat: refactor CoSTEER classes to use DSCoSTEER and update max seconds handling (#1156)

2025-08-05 18:16:10 +08:00

knowledge_base.py

feat: a unified CoSTEER to fit more scenarios (#491)

2024-11-25 16:27:34 +08:00

prompts.py

feat: Initial version if Graph RAG in KAGGLE scenario (#301)

2024-09-23 19:32:01 +08:00

proposal.py

fix: refine DSCoSTEER_eval prompts (#1157)

2025-08-06 22:55:25 +08:00

scenario.py

fix: refine prompt, equal lightgbm, discourage over hypertuning (#1072)

2025-07-15 21:58:19 +08:00

utils.py

feat: add naive experiment generator and update proposal configurations (#759)

2025-04-07 13:01:29 +08:00