Commit Graph

  • bb71c18080 feat: merge selectively (#888) Tim 2025-06-04 14:46:47 +08:00
  • a1843a9c4e feat: log reaching max time limit before breaking CoSTEER evolution (#921) you-n-g 2025-06-03 12:51:56 +08:00
  • 4aae5b6854 feat: log reaching max time limit before breaking CoSTEER evolution (#921) you-n-g 2025-06-03 12:51:56 +08:00
  • b1029cbd5a docs: update README for RD-Agent(Q) (#913) Yuante Li 2025-05-30 12:28:52 +08:00
  • 1f0bc42277 docs: update README for RD-Agent(Q) (#913) Yuante Li 2025-05-30 12:28:52 +08:00
  • 0611a0846a fix: default cost to NaN when calculation fails in LiteLLM backend (#912) you-n-g 2025-05-29 22:58:29 +08:00
  • fca945c77f fix: default cost to NaN when calculation fails in LiteLLM backend (#912) you-n-g 2025-05-29 22:58:29 +08:00
  • 4974277f1c feat: add last_exp_fb to DSTrace and update feedback retrieval usage (#910) you-n-g 2025-05-29 20:32:06 +08:00
  • 9e854a1346 feat: add last_exp_fb to DSTrace and update feedback retrieval usage (#910) you-n-g 2025-05-29 20:32:06 +08:00
  • a7c6fca8b4 chore: withdraw for policy error (#907) Tim 2025-05-29 17:23:06 +08:00
  • a9e223951f chore: withdraw for policy error (#907) Tim 2025-05-29 17:23:06 +08:00
  • 1091d5ea29 fix: use trace count as index (#909) Tim 2025-05-29 16:52:37 +08:00
  • 15e8785f6c fix: use trace count as index (#909) Tim 2025-05-29 16:52:37 +08:00
  • 63ebdb5ada fix loop_num calc logic (#911) XianBW 2025-05-29 16:40:57 +08:00
  • 249d6f9810 fix loop_num calc logic (#911) XianBW 2025-05-29 16:40:57 +08:00
  • d6ce70b551 feat: add RD-Agent-Quant scenario (#838) Yuante Li 2025-05-29 16:16:51 +08:00
  • d1019cb568 feat: add RD-Agent-Quant scenario (#838) Yuante Li 2025-05-29 16:16:51 +08:00
  • 628deade72 feat: enhance compatibility with more LLM models (#905) Haoran Pan 2025-05-29 15:21:34 +08:00
  • b0e88c7375 feat: enhance compatibility with more LLM models (#905) Haoran Pan 2025-05-29 15:21:34 +08:00
  • 29c245c6e3 fix: fix the problems weights bug (#898) Roland Minrui 2025-05-28 11:14:37 +08:00
  • 4ba28aa15f fix: fix the problems weights bug (#898) Roland Minrui 2025-05-28 11:14:37 +08:00
  • 2e39700eeb docs: add docstring for confusing columns in logs dir (#902) amstrongzyf 2025-05-27 20:54:32 +08:00
  • 14989d74f0 docs: add docstring for confusing columns in logs dir (#902) amstrongzyf 2025-05-27 20:54:32 +08:00
  • 370adbfa1e fix: refine feedback prompt (#901) Roland Minrui 2025-05-27 19:41:23 +08:00
  • 8da398f27a fix: refine feedback prompt (#901) Roland Minrui 2025-05-27 19:41:23 +08:00
  • dbaf70ce57 chore: add kill after for timeout (#899) Tim 2025-05-27 12:02:22 +08:00
  • 903403a90c chore: add kill after for timeout (#899) Tim 2025-05-27 12:02:22 +08:00
  • 3c6f9ef76d docs: update guidance for running mle-bench (#896) Haoran Pan 2025-05-26 17:43:43 +08:00
  • 8c8aa92acb docs: update guidance for running mle-bench (#896) Haoran Pan 2025-05-26 17:43:43 +08:00
  • 0109b044a0 add select_best param for log.ui.utils.compare tool function (#897) XianBW 2025-05-23 18:32:31 +08:00
  • 41095a0829 add select_best param for log.ui.utils.compare tool function (#897) XianBW 2025-05-23 18:32:31 +08:00
  • 5a62b47e95 fix: fix the bug in the regular expression matching for stdout (#890) Yuante Li 2025-05-23 14:13:31 +08:00
  • fdbffae4d7 fix: fix the bug in the regular expression matching for stdout (#890) Yuante Li 2025-05-23 14:13:31 +08:00
  • 5b47c0ab5c feat: raise policy violation (#894) Tim 2025-05-22 16:54:34 +08:00
  • b59d05b1f7 feat: raise policy violation (#894) Tim 2025-05-22 16:54:34 +08:00
  • 3e60749f70 fix: fix the bug of Exceed-LLM-Context in online merge of multi-tarce (#892) xuangu-fang 2025-05-22 16:10:00 +08:00
  • 90400c666c fix: fix the bug of Exceed-LLM-Context in online merge of multi-tarce (#892) xuangu-fang 2025-05-22 16:10:00 +08:00
  • cfa5f382aa docs: update paper report (#893) you-n-g 2025-05-22 15:37:34 +08:00
  • 6c87f722da docs: update paper report (#893) you-n-g 2025-05-22 15:37:34 +08:00
  • 9ea44be5f8 feat: new proposal (structured outputs) prompts (#887) Yuge Zhang 2025-05-22 15:08:33 +08:00
  • 74fe166687 feat: new proposal (structured outputs) prompts (#887) Yuge Zhang 2025-05-22 15:08:33 +08:00
  • 37e9912ac0 chore: organize the tool functions related to trace and summary (#889) XianBW 2025-05-21 17:20:31 +08:00
  • a12b2fe9ee chore: organize the tool functions related to trace and summary (#889) XianBW 2025-05-21 17:20:31 +08:00
  • bc9cee49ba feat: multi-trace online merge (#886) xuangu-fang 2025-05-19 17:59:42 +08:00
  • 6f29e4e3bc feat: multi-trace online merge (#886) xuangu-fang 2025-05-19 17:59:42 +08:00
  • 763dff1596 fix mypy check dependence error (#885) Linlang 2025-05-18 15:15:32 +08:00
  • e42e4dae50 fix mypy check dependence error (#885) Linlang 2025-05-18 15:15:32 +08:00
  • fe11ee92e6 chore: ui bug fix (#884) XianBW 2025-05-18 11:08:41 +08:00
  • 89deb019e9 chore: ui bug fix (#884) XianBW 2025-05-18 11:08:41 +08:00
  • 2c11752a54 chore: log storage refine (#883) XianBW 2025-05-16 18:29:59 +08:00
  • db1656bb4c chore: log storage refine (#883) XianBW 2025-05-16 18:29:59 +08:00
  • 7aea9a27dc fix: use fallback messages for missing submission and scores files (#882) you-n-g 2025-05-16 14:39:47 +08:00
  • db8eec7394 fix: use fallback messages for missing submission and scores files (#882) you-n-g 2025-05-16 14:39:47 +08:00
  • 0c97fe4ae7 update_QR_code_url (#881) Linlang 2025-05-16 14:13:40 +08:00
  • f23c6878b8 update_QR_code_url (#881) Linlang 2025-05-16 14:13:40 +08:00
  • 586349af36 fix: update DS env setup with competition volume and timeout (#878) you-n-g 2025-05-16 02:05:15 +08:00
  • 60ec58f5df fix: update DS env setup with competition volume and timeout (#878) you-n-g 2025-05-16 02:05:15 +08:00
  • 5b3f5f66cf fix: improve file tree and _walk symlink handling (#877) you-n-g 2025-05-16 00:11:25 +08:00
  • da6f662dda fix: improve file tree and _walk symlink handling (#877) you-n-g 2025-05-16 00:11:25 +08:00
  • 69e5c3a7de doc: small typo in README (#876) Xu Yang 2025-05-15 21:40:39 +08:00
  • 7a5453552d doc: small typo in README (#876) Xu Yang 2025-05-15 21:40:39 +08:00
  • b76abe839b Update README.md (#875) cslwqxx 2025-05-15 21:32:20 +08:00
  • 0279037915 Update README.md (#875) cslwqxx 2025-05-15 21:32:20 +08:00
  • c8c8e26812 add multi trace results (#873) Xu Yang 2025-05-15 20:29:52 +08:00
  • bb99485fd3 add multi trace results (#873) Xu Yang 2025-05-15 20:29:52 +08:00
  • 42ea6f106b fix debug_tpl and debug_llm saving method(#874) XianBW 2025-05-15 18:37:51 +08:00
  • 5e1292974b fix debug_tpl and debug_llm saving method(#874) XianBW 2025-05-15 18:37:51 +08:00
  • 7742a9e759 docs: update README.md (#871) you-n-g 2025-05-14 11:32:23 +08:00
  • 7943bbcc86 docs: update README.md (#871) you-n-g 2025-05-14 11:32:23 +08:00
  • 8acd24a016 chore: news MLE-bench release (#870) you-n-g 2025-05-14 11:21:13 +08:00
  • 558c3b3c45 chore: news MLE-bench release (#870) you-n-g 2025-05-14 11:21:13 +08:00
  • 54465d6e82 feat: add competition level filter and extract constants to utils (#869) you-n-g 2025-05-12 21:56:57 +08:00
  • d0b9ad8c12 feat: add competition level filter and extract constants to utils (#869) you-n-g 2025-05-12 21:56:57 +08:00
  • 90f6c94d3e fix coder bug (#868) Roland Minrui 2025-05-12 17:20:26 +08:00
  • b8fb9cf3b4 fix coder bug (#868) Roland Minrui 2025-05-12 17:20:26 +08:00
  • 7f4e5096e8 chore: custom data refine (#864) Tim 2025-05-10 17:02:12 +08:00
  • eb5f69024a chore: custom data refine (#864) Tim 2025-05-10 17:02:12 +08:00
  • a294bc74e0 feat: truncate by time (#863) you-n-g 2025-05-10 00:42:59 +08:00
  • e2bc29152d feat: truncate by time (#863) you-n-g 2025-05-10 00:42:59 +08:00
  • e71d8f6c3c feat: advanced checkpoint selectors (#790) xuangu-fang 2025-05-09 15:38:25 +08:00
  • bb96fc84f6 feat: advanced checkpoint selectors (#790) xuangu-fang 2025-05-09 15:38:25 +08:00
  • 5c7cdf298c fix: typo in workflow (#861) Xu Yang 2025-05-09 13:29:36 +08:00
  • fa53473b6c fix: typo in workflow (#861) Xu Yang 2025-05-09 13:29:36 +08:00
  • 8a0a0fa3c4 feat: log api status to mlflow (#860) Xu Yang 2025-05-09 12:20:49 +08:00
  • 1fd8abce0f feat: log api status to mlflow (#860) Xu Yang 2025-05-09 12:20:49 +08:00
  • 69c630e983 make timeout fail a hyper parameter (#859) Xu Yang 2025-05-08 21:30:44 +08:00
  • 5fecefb802 make timeout fail a hyper parameter (#859) Xu Yang 2025-05-08 21:30:44 +08:00
  • ad12fccb61 change method of cut log trace (#858) XianBW 2025-05-08 21:07:33 +08:00
  • 6fbe213f3d change method of cut log trace (#858) XianBW 2025-05-08 21:07:33 +08:00
  • 9986b5f9ce fix: refine the time/memory constraints prompt in hypothesis proposal (#856) Roland Minrui 2025-05-08 21:05:07 +08:00
  • 24c4eb7225 fix: refine the time/memory constraints prompt in hypothesis proposal (#856) Roland Minrui 2025-05-08 21:05:07 +08:00
  • eb1cefb202 fix: fixed CI execution failures caused by document builds (#857) Linlang 2025-05-08 20:35:13 +08:00
  • eed4331f0f fix: fixed CI execution failures caused by document builds (#857) Linlang 2025-05-08 20:35:13 +08:00
  • 4f5cce0607 add cache for summary, remove workspace dependency when generate summary (#854) XianBW 2025-05-08 12:24:48 +08:00
  • 9df59eb7f0 add cache for summary, remove workspace dependency when generate summary (#854) XianBW 2025-05-08 12:24:48 +08:00
  • 495063c385 fix: adjust ds_trace lookup and add stderr redirect to mlebench command (#853) you-n-g 2025-05-08 02:40:49 +08:00
  • e1d08cfe73 fix: adjust ds_trace lookup and add stderr redirect to mlebench command (#853) you-n-g 2025-05-08 02:40:49 +08:00
  • 318acb4922 fix: trace list but (#852) Xu Yang 2025-05-07 21:28:24 +08:00
  • 45b260ba37 fix: trace list but (#852) Xu Yang 2025-05-07 21:28:24 +08:00
  • 8340ab5d09 add aide.py (#851) XianBW 2025-05-07 19:59:40 +08:00