open-thought/reasoning-gym
1
0
Fork 0
mirror of https://github.com/open-thought/reasoning-gym.git synced 2026-04-19 12:58:07 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Commit graph

  • 0fb7324aaa
         Merge d73d881073 into 49b07130b3 Oliver Stanley 2026-04-18 20:21:12 +05:30
  • 0f7b8b7986 Refactor and improve code formatting for readability in combinatorics and probability modules Ritvik19 2026-04-18 19:57:16 +05:30
  • 72999eda51
         Merge fdb93a3d7d into 49b07130b3 Pierre-Hugues HUSSON 2026-04-18 19:54:31 +05:30
  • dc0d81c096 Add new probability problems dataset and extend combinatorics with additional task types Ritvik19 2026-04-18 19:26:10 +05:30
  • 9847d71dce Refactor import statements for consistency and readability across multiple test files Ritvik19 2026-04-18 17:03:18 +05:30
  • c63a596489 Refactor code formatting for improved readability across multiple files Ritvik19 2026-04-18 16:50:18 +05:30
  • 6eb252ae32 Add 13 new procedural datasets across 7 categories Ritvik19 2026-04-18 16:42:54 +05:30
  • 49b07130b3
         feat: add scoring cascade for reducing false negatives (#526) main Ritvik Rastogi 2026-04-18 01:09:15 +05:30
  • bb0a0edc61 update readme Zafir Stojanovski 2026-04-17 21:34:16 +02:00
  • f555f62292 docs: simplify scoring cascade description in README Ritvik19 2026-04-17 16:25:30 +00:00
  • af8d3bb6b3 docs: shorten scoring cascade section in README Ritvik19 2026-04-17 16:20:29 +00:00
  • 672e2cc9f9 docs: add scoring cascade example to Quickstart section Ritvik19 2026-04-17 14:36:17 +00:00
  • d6a5a8a9f1 style: fix black and isort formatting Ritvik19 2026-04-17 14:32:25 +00:00
  • 83fcceb317 feat: add scoring cascade for reducing false negatives in answer verification Ritvik19 2026-04-17 13:31:28 +00:00
  • 4de896375f
         Merge 70af0ad699 into 437e0b49c4 joesharratt1229 2026-03-29 08:50:18 +02:00
  • 437e0b49c4
         bump version to v0.1.26.dev0 (#525) Andreas Köpf 2026-03-28 14:55:43 +01:00
  • 33fa205104 bump version to v0.1.26.dev0 Andreas Koepf 2026-03-28 14:43:02 +01:00
  • 21e6d2a9a5
         add path-star task environment (#499) v0.1.25 Oliver Stanley 2026-03-28 00:07:49 +00:00
  • 8fb9513eea test tweak Oliver Stanley 2026-03-27 15:41:12 +00:00
  • b9b0ddea5b validation tweak Oliver Stanley 2026-03-27 15:40:43 +00:00
  • 89cd82c647 fixes Oliver Stanley 2026-03-27 15:35:06 +00:00
  • d26663fb3f
         Fix impossible_ratio not being respected in knight_swap (#521) (#524) Zafir Stojanovski 2026-03-27 16:18:08 +01:00
  • 304558a673 Fix impossible_ratio not being respected in knight_swap (#521) Zafir Stojanovski 2026-03-26 18:12:04 +01:00
  • 49b1dbbcce
         Fix misleading instruction in shortest_path asking for "length" instead of path (#523) Zafir Stojanovski 2026-03-25 13:02:23 +01:00
  • 9886b582b2 Fix misleading instruction in shortest_path asking for "length" instead of path Zafir Stojanovski 2026-03-25 11:08:54 +01:00
  • 9a91d92ca6
         Update README.md with new project (#519) Zafir Stojanovski 2026-03-15 17:13:56 +01:00
  • 4371b82788 Update README.md with new project Zafir Stojanovski 2026-03-15 15:11:37 +01:00
  • 51bbe8c62b
         Update README.md with new project (#518) Zafir Stojanovski 2026-03-15 13:53:52 +01:00
  • 235b5629f7
         Fix/cryptarithm multiple solutions (#517) theblackcat102 2026-03-15 20:53:26 +08:00
  • 6e030c174a Apply black formatting fixes Andreas Koepf 2026-03-15 13:49:25 +01:00
  • d0ca940502 Update README.md with new project Zafir Stojanovski 2026-03-15 08:07:01 +01:00
  • 6a9f3860a0 [fix] clean up comments theblackcat102 2026-03-06 07:53:30 +08:00
  • 467eb4da82 [fix] issue #516 of cryptarithm validation issue theblackcat102 2026-03-06 00:43:56 +08:00
  • 5dcca08309
         Add assertion for maze constraints and limit _random_floor_cell attempts (#515) Gjorgji Noveski 2026-01-16 09:56:39 +01:00
  • 353020c436 Removed assertion check due not working for all maze configurations Gjorgji Noveski 2026-01-16 09:50:55 +01:00
  • da424498e4 Fixed maze grid size validation formula Gjorgji Noveski 2026-01-15 22:34:14 +01:00
  • 6ed7fe8de1 Added assertion and infinite loop fix for maze environment Gjorgji Noveski 2026-01-05 01:42:42 +01:00
  • 7d68a6cc70
         Fix(reasoning_gym/games/countdown): Resolve SymPy parsing conflict for 10+ input numbers (#514) SII-Whereby 2025-12-15 19:05:38 +08:00
  • 05e279c18d
         Improve readability of CountdownDataset initialization SII-Whereby 2025-12-10 09:22:12 +08:00
  • 8a402402e5
         Remove trailing-whitespace SII-Whereby 2025-12-10 09:21:00 +08:00
  • c24c439e17
         Implement test for min_numbers exceeding 10 SII-Whereby 2025-12-09 10:43:00 +08:00
  • 7b6283e81b
         Add expr_str to return values in countdown.py SII-Whereby 2025-11-30 22:12:33 +08:00
  • 85629bdfec
         Refactor expression generation and substitution logic SII-Whereby 2025-11-30 21:25:06 +08:00
  • de2e89d21d
         Codeio prompt fix (#513) Ramiro R. C. 2025-11-13 07:48:20 -03:00
  • 4a37284777 corrected gallery examples too Ramiro Rodriguez Colmeiro 2025-11-12 12:49:09 -03:00
  • 7fdba32046 prompr fix to request more specific JSON responses Ramiro Rodriguez Colmeiro 2025-11-12 12:47:54 -03:00
  • 2c4e45d9a9
         Update spiral_matrix.py (#511) Zafir Stojanovski 2025-10-06 13:02:32 +02:00
  • 326e999cad Improve spiral matrix instructions with clearer movement description and hint Andreas Koepf 2025-10-06 12:53:13 +02:00
  • 578ba55d2f
         Update spiral_matrix.py Zafir Stojanovski 2025-10-06 12:31:50 +02:00
  • bcc68c5fee
         Update README.md with new project (#510) Zafir Stojanovski 2025-10-02 17:43:32 +02:00
  • 85be4daeca
         Update README.md with new project Zafir Stojanovski 2025-10-02 17:37:52 +02:00
  • 15d7f027e4
         add mila projects (#508) Zafir Stojanovski 2025-09-29 15:37:13 +02:00
  • dd3117bbaf
         bump version to v0.1.25.dev0 (#509) Andreas Köpf 2025-09-29 15:36:30 +02:00
  • aecfde4c84 bump version to v0.1.25.dev0 Andreas Koepf 2025-09-29 09:33:15 +02:00
  • bb3d9f1add add mila projects Zafir Stojanovski 2025-09-28 11:46:18 +02:00
  • 2f9eaee32a
         fix: Register missing coin_flip (#507) v0.1.24 Zafir Stojanovski 2025-09-15 14:23:30 +02:00
  • 44d4786954 lint Zafir Stojanovski 2025-09-12 13:40:44 +02:00
  • 05e5f63dc7 register missing coin_flip Zafir Stojanovski 2025-09-12 13:39:01 +02:00
  • 3fcb8642c6
         (README): add gensyn paper (#506) Zafir Stojanovski 2025-09-11 17:11:04 +02:00
  • 0ae36138fc remove badge Zafir Stojanovski 2025-09-11 15:35:30 +02:00
  • 6d762822c9 update badge Zafir Stojanovski 2025-09-11 15:30:47 +02:00
  • ee81ec0c75 gensyn paper Zafir Stojanovski 2025-09-11 15:26:35 +02:00
  • b0815043a2
         Add probability dataset (initial: Coin Flip dataset + curriculum) (#505) Kumar Anant 2025-09-06 20:29:23 +05:30
  • a2c0c7b391 Fix formatting with pre-commit kumaranant1 2025-09-06 19:37:08 +05:30
  • 32008c08fe create init and add difficulty metadata for curriculum kumaranant1 2025-09-06 16:07:27 +05:30
  • 4205bffddb Add CoinFlip probability dataset and curriculum with test script kumaranant1 2025-09-06 05:06:57 +05:30
  • b399c658ca
         Add OptimalThinkingBench to Projects Using RG (#503) Rich Jones 2025-08-24 21:36:11 +02:00
  • 569b7d91b5
         Update README.md Rich Jones 2025-08-24 20:52:43 +02:00
  • d7a3a81681 add meta project Zafir Stojanovski 2025-08-24 18:43:25 +02:00
  • e3afba8b5e
         Add OptimalThinkingBench to Projects Using RG Rich Jones 2025-08-24 18:35:49 +02:00
  • 02b7fac863
         fix encoding to be able to run on win (#502) Denini Gabriel 2025-08-18 05:19:45 -03:00
  • 1851d10f63 fix enconding to be able to run on win Denini Gabriel 2025-08-16 00:49:52 +00:00
  • b8aa55704b
         add discord link (#500) Zafir Stojanovski 2025-08-05 10:57:46 +02:00
  • bc929b7fa8 add discord link Zafir Stojanovski 2025-08-04 12:50:20 +02:00
  • 678622faec add imports Oliver 2025-08-03 16:00:49 +01:00
  • 641712e7fa rm teacherless mode Oliver 2025-08-03 15:59:56 +01:00
  • 18ff9868df fix for paper spec Oliver 2025-08-03 15:42:59 +01:00
  • d795ba68c9 typos Oliver 2025-08-02 22:56:54 +01:00
  • fc02d1af5a draft path-star task Oliver 2025-08-02 22:40:00 +01:00
  • 86c4f8552f
         add GEM to projects using RG (#498) Zafir Stojanovski 2025-08-02 10:09:53 +02:00
  • 93b3c9f20a add GEM to projects using RG Zafir Stojanovski 2025-08-02 09:51:13 +02:00
  • 0e4582f83b
         fix(evaluation): Add instructions for running on MMLU Pro (#497) Zafir Stojanovski 2025-08-01 16:27:56 +02:00
  • 6d17c4565b remove --fewshot_as_multiturn Zafir Stojanovski 2025-08-01 15:55:31 +02:00
  • 0e6b2afbe5 lint Zafir Stojanovski 2025-08-01 14:53:20 +02:00
  • 41d3af95be add instructions for mmlu pro, format instructions for math benchmarks Zafir Stojanovski 2025-08-01 14:50:51 +02:00
  • a969d8ef05
         feat(curriculum): Knights and Knaves configs (#488) Zafir Stojanovski 2025-07-31 10:18:05 +02:00
  • 53359e50c6 fix tests Zafir Stojanovski 2025-07-31 09:30:43 +02:00
  • cf99528dbe
         Run categories in parallel (#492) Szymon Ożóg 2025-07-30 19:11:27 +02:00
  • 70af0ad699
         Update load_fsdp_to_hf.py feat/curriculum-exp joesharratt1229 2025-07-28 15:57:15 +01:00
  • 62887ad1fc
         Update load_fsdp_to_hf.py joesharratt1229 2025-07-28 15:56:16 +01:00
  • 3393d22611 added training and evaluation curr conf joesharratt1229 2025-07-28 15:51:19 +01:00
  • cc47ed4044 added training and evaluation curr conf joesharratt1229 2025-07-28 15:51:19 +01:00
  • d73d881073 reps feat/multi-curriculum-exp Oliver 2025-07-28 12:52:31 +01:00
  • 63ceab7b1e set eval repeats to 3 Zafir Stojanovski 2025-07-28 11:45:15 +00:00
  • 523d56f019 add graphs eval configs Oliver 2025-07-28 12:21:31 +01:00
  • e5671b2f7b return binary scoring Zafir Stojanovski 2025-07-28 10:27:12 +00:00
  • 39364e0d16 dtype model eval Zafir Stojanovski 2025-07-28 10:17:06 +00:00
  • 63ad2dc35e lint Zafir Stojanovski 2025-07-28 09:30:47 +02:00
  • b29093e2ee
         Add option to increase timeout (#493) Szymon Ożóg 2025-07-28 06:26:09 +02:00
  • 2ab408e2d6 Run categories in parallel SzymonOzog 2025-07-27 08:46:54 -07:00