d344fd680f
ckpt 8
2026-01-19 08:20:14 +00:00
1fc1a6e14f
ckpt 7 fix bug
2026-01-14 10:45:35 +00:00
b6cd8133c4
fix cuda problem/ckpt7
2026-01-13 07:36:06 +00:00
aa8637a10c
ckpt 7
2026-01-09 07:50:51 +00:00
38b9736590
Evo ( #1322 )
...
* add ckpt 7
* add ckpt 8
2026-01-09 15:33:10 +08:00
f8904d9739
add ckpt 6
2025-12-18 10:23:29 +00:00
35c60d9015
add new ckpt
2025-12-08 10:09:38 +00:00
d0aa7324fa
fix bug 11
2025-11-25 10:43:01 +00:00
0fd51dbed3
fix bug 10
2025-11-25 09:20:27 +00:00
89a3a610c4
fix bug 9
2025-11-24 16:22:47 +00:00
d20781d44a
fix bug 8
2025-11-24 11:17:08 +00:00
4784b75fec
fix bug 7
2025-11-24 09:31:34 +00:00
1b28ffcb41
add more competition
2025-11-24 08:38:31 +00:00
9356071cc9
fix bug 6
2025-11-21 10:45:56 +00:00
78e6b1ad3a
fix bug 5
2025-11-20 09:32:43 +00:00
f83cfb5db3
add two type reward model
2025-11-20 08:25:10 +00:00
1d7ee2c7d3
fix bug 4
2025-11-19 16:50:13 +00:00
a62870c83b
fix pydantic-ai-bug :(
2025-11-19 10:16:01 +00:00
6258915da3
fix pydantic-ai version
2025-11-19 07:57:15 +00:00
fabcc846a2
fix bug 3
2025-11-18 08:12:44 +00:00
b45aac0ad8
fix bug 2
2025-11-18 07:33:57 +00:00
9111b0cd36
fix bug
2025-11-18 07:30:19 +00:00
0453af1f12
fix bug remove torch
2025-11-18 07:29:47 +00:00
62de6d10f2
add
2025-11-18 02:24:49 +00:00
3d24be04b7
add install transformers
2025-11-17 14:57:26 +00:00
7d3dc7f40b
fix bug
2025-11-17 11:12:09 +00:00
98ca9cf455
add path online
2025-11-17 10:11:56 +00:00
2fd918c703
add avg win reward model
2025-11-17 08:51:55 +00:00
5dbb355081
Merge remote-tracking branch 'origin/main' into evo
2025-10-24 07:22:48 +00:00
c2defc195e
fix litellm log content ( #1278 )
2025-10-24 12:30:30 +08:00
10655948cc
Merge remote-tracking branch 'origin/main' into evo
2025-10-23 09:21:32 +00:00
417766ee36
fix: refine task scheduling logic in MultiProcessEvolvingStrategy for… ( #1275 )
...
* fix: refine task scheduling logic in MultiProcessEvolvingStrategy for improved handling of feedback in improve mode
* fix: add empty implementation for skipped tasks in MultiProcessEvolvingStrategy
2025-10-23 17:09:18 +08:00
c337494c12
Merge remote-tracking branch 'origin/main' into evo
2025-10-23 08:33:00 +00:00
ddec8c382f
add reward model
2025-10-23 08:30:49 +00:00
961e56102c
fix: enhance feedback handling in MultiProcessEvolvingStrategy for improved task evolution ( #1274 )
2025-10-23 16:00:23 +08:00
9344635695
feat: add improve_mode to MultiProcessEvolvingStrategy for selective task implementation ( #1273 )
2025-10-22 17:35:18 +08:00
40876e2085
fix: replace hardcoded ChromeDriver path with webdriver-manager ( #1271 )
2025-10-20 22:15:44 +08:00
a0cd1025c1
feat: add a rag mcp in proposal ( #1267 )
...
* add simple rag mcp
* add rag_agent in expGen v2
* add conf config for research rag
* fix CI
* refactor: move context7 and rag config files to new conf modules
* make rag agent general
* fix CI
---------
Co-authored-by: Young <afe.young@gmail.com >
2025-10-20 16:46:25 +08:00
c73f67affe
fix: fix mcts ( #1270 )
...
* init mcts class
* full ver of MCTS
* auto-lint
* make MCTS feedback in exp-gen()
* refactor: move reset logic from Trace to ExpGen and update usage accordingly
* fix: reinitialize trace on consecutive errors in DataScienceRDLoop
* feat: add reset method to BaseScheduler and call in MCTSScheduler reset
* style: reorder imports for consistency and PEP8 compliance
* lint
* fix observe_feedback
* fix bug
* remove uncommited_rec_status
* more simple
* refactor: move commit observation logic to process_uncommitted_nodes method
* docs: add TODO comment about rule-based virtual root node expansion
* add score reward
* fix bug
* fix small bug
* lint
* change reward
* small small change
* autolint
---------
Co-authored-by: xuangu-fang <xuangufang@gmail.com >
Co-authored-by: Young <afe.young@gmail.com >
2025-10-17 16:57:28 +08:00
6f86863b63
feat(mcp): cache with one-click toggle ( #1269 )
...
* feat: enable cache in mcp
* refactor: remove redundant setting
* fix: conflicts during installation
---------
Co-authored-by: Linlang <Lv.Linlang@hotmail.com >
2025-10-17 16:30:59 +08:00
13890e0bbc
feat: mcts policy based on trace scheduler ( #1203 )
...
* init mcts class
* full ver of MCTS
* auto-lint
* make MCTS feedback in exp-gen()
* refactor: move reset logic from Trace to ExpGen and update usage accordingly
* fix: reinitialize trace on consecutive errors in DataScienceRDLoop
* feat: add reset method to BaseScheduler and call in MCTSScheduler reset
* style: reorder imports for consistency and PEP8 compliance
* lint
* fix observe_feedback
* fix bug
* remove uncommited_rec_status
* more simple
* refactor: move commit observation logic to process_uncommitted_nodes method
* docs: add TODO comment about rule-based virtual root node expansion
* add score reward
* fix bug
* fix small bug
* lint
* change reward
* lint
---------
Co-authored-by: Young <afe.young@gmail.com >
Co-authored-by: jingyuanlm <842442862@qq.com >
Co-authored-by: amstrongzyf <amstrongzyf@126.com >
2025-10-17 16:21:39 +08:00
0f722e1ce7
fix: model/factor experiment filtering in Qlib proposals ( #1257 )
...
* Fix model/factor experiment filtering in Qlib proposals
* fix(dockerfile): install coreutils to resolve timeout command error (#1260 )
* chore: remove unused experiment_list and target_list from Qlib proposals
* fix CI
* fix target list
---------
Co-authored-by: Xu Yang <peteryang@vip.qq.com >
2025-10-10 22:49:46 +08:00
07f89b013e
fix(dockerfile): install coreutils to resolve timeout command error ( #1260 )
2025-10-10 10:44:22 +08:00
9d46a68a36
fix: prevent JSON content from being added multiple times during retries ( #1255 )
2025-10-02 09:45:58 +08:00
f360d0a212
fix(docs): update rdagent ui with correct params ( #1249 )
2025-09-23 16:20:00 +08:00
5a78c89cee
fix: merge candidates ( #1254 )
...
* fix: add hypotheses_candidates
2025-09-22 21:04:07 +08:00
833296084f
feat: update README with latest paper acceptance to NeurIPS 2025 ( #1252 )
...
* feat: update README with latest news and announcements
* update readme
2025-09-19 10:58:07 +08:00
2afef703ca
feat: add user interaction in data science scenario ( #1251 )
...
* feat: add interactor classes and user interaction handling for experiments
* update code
* use fragment retry mechanism instead of rerun()
* fix a bug
* integrate user instructions into proposal and coder
* fix CI
* fix CI
* feat: add approval option for user instructions submission
* feat: enhance user instructions handling in Task and DSExperiment classes
* fix CI
* add user instructions into hypothesis rewrite
* add interface to command line
---------
Co-authored-by: Bowen Xian <xianbowen@outlook.com >
2025-09-18 11:10:12 +08:00
dbe04eaa58
chore: valid selector update ( #1248 )
...
* chore: add medal info
* return sota_exp_stat
* update hit check
* update experiment
* udpate experiment
* extract log
* remove old log folder
* update candidates
* keep highest score
* early stop if no medal candidate
2025-09-17 15:48:16 +08:00
4dfb8a130b
fix: add json format response fallback to prompt templates ( #1246 )
...
* fix: add json format response fallback to prompt templates
* more json prompt
2025-09-15 23:27:24 +08:00
jingyuanlm