586623084f
feat: streamline hyperparameter tuning checks and update evaluation g… ( #1167 )
...
* feat: streamline hyperparameter tuning checks and update evaluation guidelines
* fix task_gen json check
2025-08-08 13:49:01 +08:00
9c190e3268
feat: improve fallback handling in CoSTEER and add GPU usage guidelin… ( #1165 )
...
* feat: improve fallback handling in CoSTEER and add GPU usage guideline in share.yaml
* update prompt
* update
2025-08-07 15:52:55 +08:00
7f90253c4c
add parent & root node in trace page ( #1164 )
2025-08-07 15:02:46 +08:00
bfa452541c
feat: add reasoning attribute to DSRunnerFeedback for enhanced evaluation context ( #1162 )
2025-08-07 00:50:08 +08:00
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
1b84f7b754
fix: ignore case when checking metric name ( #1160 )
...
* fix: ignore case when checking metric name
* add case-sensitive to prompts
---------
Co-authored-by: amstrongzyf <amstrongzyf@126.com >
2025-08-06 20:54:08 +08:00
d771b26a26
chore: show timeline and change load_times ( #1161 )
...
* show timeline, deperacate old load_times
* fix bug
2025-08-06 18:42:17 +08:00
7e15b5e200
feat: prob-based trace scheduler ( #1131 )
...
* draft prob-based trace scheduler
* refactor ProbabilisticScheduler
* auto lint
* keep random, Sota-based, length-based trace schedluer
* lint
* example
* example
* refactor
* add inverse option for sota Scheduler
* add trace_Scheduler in conf
* lint
* add scheduler_temperature
---------
Co-authored-by: Young <afe.young@gmail.com >
2025-08-06 16:42:51 +08:00
6b50670f2e
fix loop step time log problem ( #1158 )
2025-08-06 15:43:28 +08:00
35c209b092
feat: enable finetune llm ( #1055 )
...
* feat: start with previous workspace
* feat: finetune llm
* add PrevModelLoadEvaluator
---------
Co-authored-by: Young <afe.young@gmail.com >
Co-authored-by: v-jianwan <v-jianwan@microsoft.com >
Co-authored-by: you-n-g <you-n-g@users.noreply.github.com >
2025-08-06 12:24:44 +08:00
c111966d19
feat: refactor CoSTEER classes to use DSCoSTEER and update max seconds handling ( #1156 )
...
* feat: refactor CoSTEER classes to use DSCoSTEER and update max seconds handling
* remove useless line
* enable time_ratio_limit_to_enable_hyperparameter_tuning
2025-08-05 18:16:10 +08:00
f03b1b918d
feat: create Jupyter notebook pipeline file based on main.py file ( #1134 )
...
* First commit
* isort
* black
* tweak prompt
* fix for argparse
* fix typo
* add e2e
* Add test files, clean
* fix black settings
* revert
* fix trailing
* remove extra
* comment
* small fix, updated prompt
* Fix argparse
* small improvements
* fix for merge
* fix for merge
2025-08-05 18:06:57 +08:00
56ed919b2e
docs: update configuration docs ( #1155 )
...
* update configuration docs
* update configuration docs
* update configuration docs
2025-08-05 15:48:28 +08:00
b4117cf58a
feat: add mask inference in debug mode ( #1154 )
2025-08-05 14:09:12 +08:00
80c953d405
fix: add metric in scores.csv and avoid reading sample_submission.csv ( #1152 )
...
* add scores.csv metric name in both task_gen and coder
* a little fix to column names
* small fix
* avoid sample submission read in task_gen
* avoid sample_submission reading in coding
* code change summary bug fix
* little update
* little refinement to eval
* refine coder and runner eval prompts
---------
Co-authored-by: Xu Yang <peteryang@vip.qq.com >
2025-08-04 19:53:08 +08:00
811d4e7631
feat: enhance timeout handling in CoSTEER and DataScience scenarios ( #1150 )
...
* add prev loops to runner history
* fix evolving history
* fix bug on initializing feedback without final decision
* reformat
* refine
* add comments
* feat: enhance timeout handling in CoSTEER and DataScience scenarios
---------
Co-authored-by: Xu <v-xuminrui@microsoft.com >
2025-08-04 17:44:51 +08:00
2426a1dc67
feat: add previous runner loops to runner history ( #1142 )
...
* add prev loops to runner history
* fix evolving history
* fix bug on initializing feedback without final decision
* reformat
* refine
* add comments
* fix ci
* a little refinement
* fix CI
---------
Co-authored-by: Xu <v-xuminrui@microsoft.com >
Co-authored-by: Xu Yang <peteryang@vip.qq.com >
2025-08-04 17:38:27 +08:00
c2bde6dcc3
save more time info ( #1151 )
2025-08-04 17:28:25 +08:00
c985e34531
change something for ui compatiblity ( #1149 )
2025-08-04 12:40:35 +08:00
5565fbe8a4
fix ( #1148 )
...
Co-authored-by: Xu <v-xuminrui@microsoft.com >
2025-08-02 18:36:31 +08:00
52bf46318f
chore: overwrite sota exp stat in summary page ( #1146 )
...
* overwrite sota exp stat in summary page
* remove unused import
2025-08-01 18:55:26 +08:00
8a3e42d7fe
feat: add show_hard_limit option and update time limit handling in DataScience settings ( #1144 )
2025-08-01 18:32:15 +08:00
d0832eb5ff
bug fix ( #1145 )
2025-08-01 18:07:19 +08:00
7134a51afa
fix: fix some bugs in RD-Agent(Q) ( #1143 )
...
* fix some bugs in RD-Agent(Q)
* fix factor from report
* fix ci
2025-08-01 13:20:09 +08:00
bd8a16d92f
fix: ignore RuntimeError for shared workspace double recovery ( #1140 )
...
* fix: ignore RuntimeError for shared workspace double recovery
* add print
2025-07-31 21:02:37 +08:00
38aa6eb046
use popover instead of expander ( #1138 )
2025-07-31 18:14:38 +08:00
28ceb41e1c
fix: clear ws_ckp after extraction to reduce workspace object size ( #1137 )
2025-07-31 18:10:32 +08:00
7fc09169bc
feat: fallback to acceptable results ( #1129 )
...
* refactor: add is_acceptable, fallback logic and generify evolving agent
* refine lint
* small
* lint
* lint
* lint
* feat: add is_acceptable to CoSTEERMultiFeedback
* feat: add in-memory workspace checkpoint and recovery
* feat: preserve symbolic links in workspace checkpoints and recovery
* lint
* lint
* feat: limit workspace checkpoint to files under 100KB
* feat: add workspace checkpoint size limit setting
* prompt
* lint
2025-07-31 17:53:18 +08:00
fd6cd3950c
fix: remove unused imports in data science scenario module ( #1136 )
2025-07-31 17:05:14 +08:00
6a4998154d
feat: add time ratio limit for hyperparameter tuning in Kaggle settin… ( #1135 )
...
* feat: add time ratio limit for hyperparameter tuning in Kaggle settings and update evaluator logic
* add recommend time limit
* remove 25% hard line
* small fix
2025-07-31 16:47:19 +08:00
305eff1c5e
feat: enhance timeout management and knowledge base handling in CoSTEER components ( #1130 )
...
* feat: enhance timeout management and knowledge base handling in CoSTEER components
* fix a little bug
* fix small bug
* fix a small bug
* Update rdagent/scenarios/data_science/loop.py
Co-authored-by: you-n-g <you-n-g@users.noreply.github.com >
* add scale check
* fix a small bug
* fix CI
* use dynamic chat_token_limit & remove repeated lines
* fix CI
* remove useless comment
* fix small bug
* update draft appendix
* fix prompt
* add code correctness as top priority
---------
Co-authored-by: you-n-g <you-n-g@users.noreply.github.com >
2025-07-31 13:06:28 +08:00
600d159e86
fix: update requirements.txt's streamlit ( #1133 )
2025-07-30 21:30:53 +08:00
0ccb6e6d56
log time duration when call LLM and show timeout ratio of coding & running in trace UI ( #1128 )
2025-07-29 17:54:29 +08:00
e0519b56ae
feat: add coder check and give more time ( #1127 )
...
* feat: introduce max_seconds_multiplier for timeout management across components
* avoid using assert in test
* hot fix a very small bug
* runner multiply twice
* revert feedback change
* add a switch to longer timeout
2025-07-29 14:59:38 +08:00
a6703aa313
feat: add hypo_critic and hypo_rewrite in proposal ( #1106 )
...
add hypo_critique and hypo_rewrite in proposal.py, controlled by `DS_RD_SETTING.enable_hypo_critique_rewrite` (default True)
2025-07-29 14:20:09 +08:00
eb70333b77
small fix to runner eval order to prevent both final decision and hyperparameter decision to be true
...
Co-authored-by: Xu <v-xuminrui@microsoft.com >
2025-07-29 13:31:35 +08:00
4cee886c80
fix current_selection maybe empty ( #1125 )
2025-07-29 11:56:59 +08:00
e19fe4b233
fix find last SOTA diff ( #1124 )
2025-07-29 10:56:41 +08:00
bbcee389b4
chore: implement runtime_env func ( #1104 )
...
* implement runtime_env func for quant
* add runtime_info code
* add runtime env information to the prompt
* format with black
* optimize get_runtime_env code
* delete unnecessary files
* some refinement
* fix fin_quant bugs
---------
Co-authored-by: Xu Yang <peteryang@vip.qq.com >
2025-07-28 14:19:41 +08:00
514c191b75
fix: fix code diff bug ( #1115 )
...
* fix code diff bug
* fix minor bug
* reformat
* fix minor bug
* fix
* fix
* fix the prefix type
---------
Co-authored-by: Xu <v-xuminrui@microsoft.com >
2025-07-26 22:51:59 +08:00
15fa03d415
fix sota_exp is None ( #1121 )
2025-07-25 11:53:26 +08:00
13f49062a4
fix a small bug in feedback ( #1120 )
2025-07-24 22:33:08 +08:00
5025448e84
add lite curves figure ( #1119 )
2025-07-24 20:11:09 +08:00
59a2d7f91d
fix curve ( #1118 )
2025-07-24 19:15:01 +08:00
e92cd99450
chore: some ui features change ( #1117 )
...
* add some todos
* fix bug
* fix leaderboard download function
* summary stat fix
* show medal
* show SOTA Loop
* fix CI
2025-07-24 18:50:29 +08:00
7a5dd566f5
chore: avoid more traces during merge ( #1108 )
...
* avoid more traces during merge
* restore change
* remove duplicate experiments
* add dropped pool
* use scenario
* remove drop_pool
* use max_sota_retrieved_num
2025-07-24 18:27:23 +08:00
5e959a5f59
feat: analyze feedback based on sota numbers ( #1116 )
...
* give sota numbers to feedback
* refine prompt
2025-07-24 14:17:52 +08:00
bbb008c95e
fix cli command type checker ( #1114 )
2025-07-23 19:43:25 +08:00
0c3d0cd327
fix: prompt yaml ( #1112 )
...
* small fix to prompt yaml
* shrink the content
* remove parallel.py
2025-07-23 15:03:59 +08:00
067c5a3334
fix health check bug ( #1111 )
2025-07-23 12:29:09 +08:00
Xu Yang