Zafir Stojanovski
49b1dbbcce
Fix misleading instruction in shortest_path asking for "length" instead of path ( #523 )
...
The prompt asked to "find the length of the shortest path" but the expected
answer is a sequence of directions. This caused models to answer with a number
instead of directions, degrading evaluation results.
Closes #522
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-25 13:02:23 +01:00
Zafir Stojanovski
9a91d92ca6
Update README.md with new project ( #519 )
...
Add Apple's Multilingual Reasoning Gym paper to the projects list.
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 17:13:56 +01:00
Zafir Stojanovski
51bbe8c62b
Update README.md with new project ( #518 )
...
Add NVIDIA Nemotron 3 Super to the list of projects using Reasoning Gym.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-15 13:53:52 +01:00
theblackcat102
235b5629f7
Fix/cryptarithm multiple solutions ( #517 )
...
* [fix] issue #516 of `cryptarithm` validation issue
---------
Co-authored-by: Andreas Koepf <andreas.koepf@provisio.com>
2026-03-15 13:53:26 +01:00
Gjorgji Noveski
5dcca08309
Add assertion for maze constraints and limit _random_floor_cell attempts ( #515 )
...
* Added assertion and infinite loop fix for maze environment
* Fixed maze grid size validation formula
* Removed assertion check due not working for all maze configurations
2026-01-16 09:56:39 +01:00
SII-Whereby
7d68a6cc70
Fix(reasoning_gym/games/countdown): Resolve SymPy parsing conflict for 10+ input numbers ( #514 )
...
* Refactor expression generation and substitution logic
Updated symbol naming and added safe replacement for expressions.
* Add expr_str to return values in countdown.py
Modified return statement to include the modified expression string.
* Implement test for min_numbers exceeding 10
Add test for CountdownDataset with more than 10 numbers
* Remove trailing-whitespace
* Improve readability of CountdownDataset initialization
Refactor CountdownDataset initialization for readability.
2025-12-15 11:05:38 +00:00
Ramiro R. C.
de2e89d21d
Codeio prompt fix ( #513 )
...
* prompr fix to request more specific JSON responses
* corrected gallery examples too
2025-11-13 11:48:20 +01:00
Zafir Stojanovski
2c4e45d9a9
Update spiral_matrix.py ( #511 )
...
* Improve spiral matrix instructions with clearer movement description and hint
---------
Co-authored-by: Andreas Koepf <andreas.koepf@provisio.com>
2025-10-06 13:02:32 +02:00
Zafir Stojanovski
bcc68c5fee
Update README.md with new project ( #510 )
2025-10-02 17:43:32 +02:00
Zafir Stojanovski
15d7f027e4
add mila projects ( #508 )
2025-09-29 14:37:13 +01:00
Andreas Köpf
dd3117bbaf
bump version to v0.1.25.dev0 ( #509 )
2025-09-29 14:36:30 +01:00
Zafir Stojanovski
2f9eaee32a
fix: Register missing coin_flip ( #507 )
...
* register missing coin_flip
* lint
2025-09-15 14:23:30 +02:00
Zafir Stojanovski
3fcb8642c6
(README): add gensyn paper ( #506 )
...
* gensyn paper
2025-09-11 17:11:04 +02:00
Kumar Anant
b0815043a2
Add probability dataset (initial: Coin Flip dataset + curriculum) ( #505 )
2025-09-06 15:59:23 +01:00
Rich Jones
b399c658ca
Add OptimalThinkingBench to Projects Using RG ( #503 )
...
* Add OptimalThinkingBench to Projects Using RG
* Update README.md
2025-08-24 21:36:11 +02:00
Denini Gabriel
02b7fac863
fix encoding to be able to run on win ( #502 )
2025-08-18 09:19:45 +01:00
Zafir Stojanovski
b8aa55704b
add discord link ( #500 )
2025-08-05 09:57:46 +01:00
Zafir Stojanovski
86c4f8552f
add GEM to projects using RG ( #498 )
2025-08-02 09:09:53 +01:00
Zafir Stojanovski
0e4582f83b
fix(evaluation): Add instructions for running on MMLU Pro ( #497 )
...
* add instructions for mmlu pro, format instructions for math benchmarks
* lint
* remove `--fewshot_as_multiturn`
2025-08-01 16:27:56 +02:00
Zafir Stojanovski
a969d8ef05
feat(curriculum): Knights and Knaves configs ( #488 )
...
* configs
* reduce complexity of curriculum
* update lower bound
* add failure threshold
* update last_k
* update thresholds for success and failure
* update curriculum file as well
* update run name for noncurriculum
* lint
* dtype model eval
* return binary scoring
* set eval repeats to 3
* fix tests
2025-07-31 10:18:05 +02:00
Szymon Ożóg
cf99528dbe
Run categories in parallel ( #492 )
2025-07-30 18:11:27 +01:00
Szymon Ożóg
b29093e2ee
Add option to increase timeout ( #493 )
2025-07-28 06:26:09 +02:00
Zafir Stojanovski
0f5352e5cd
fix: Training README.md ( #491 )
...
* Update README.md in `training`
* add pip install for verl
2025-07-27 11:56:00 +02:00
joesharratt1229
4b60c32978
Curr exp ( #487 )
...
* began curr exp
* added holdout words
* updated config
* added context
* updated base curriculum
* updaed
* updated curriculum
* updated
* updated
* updated automatic flag
* updated ray trainer
* update
2025-07-25 20:38:47 +01:00
theblackcat102
2d19f13e0f
[ fix #484 ] resolve basic_arithmetic fails when size is large ( #485 )
...
* [fix] resolve basic_arithmetic fails when size is large by replacing zero divisor with 1
2025-07-07 09:46:23 +01:00
Zafir Stojanovski
bf451d5197
Update README.md ( #483 )
2025-07-05 01:57:21 +02:00
joesharratt1229
1c98584f28
Feat/unsloth example ( #482 )
...
* cleaned up examples
* updated failing hooks
* updated readme
* corrected linting checks
2025-06-28 17:04:38 +01:00
Rich Jones
d9cd20c174
Update README.md (RLSwarm GenRL) ( #480 )
2025-06-26 10:20:45 +01:00
Oliver Stanley
1c9ed2e0eb
better usage demo in readme ( #477 )
...
* better usage demo in readme
* example of non-default configs
2025-06-25 13:38:25 -07:00
joesharratt1229
876e0aa440
corrected countdown issue ( #479 )
2025-06-25 13:37:04 -07:00
Zafir Stojanovski
c2ac6fae32
Update README.md ( #475 )
2025-06-24 14:19:11 +01:00
Zafir Stojanovski
56ce2e79a7
tutorial(training): Add a minimal example with trl ( #473 )
...
* v0
* 2 gpu setup
* improve parsing from yaml
* update yaml dataset example
* remove restriction on flash attn
* more comments
* first version of the readme
* pin torch
* simplify requirements
* just flash attn
* use set env instead
* simpler set env
* readme
* add wandb project to setup
* update template
* update model id
* post init to capture the config and weight
* extract metadata
* update config
* update dataset config
* move env for wandb project
* pre-commit
* remove qwen-math from training
* more instructions
* unused import
* remove trl old
* warmup ratio
* warmup ratio
* change model id
* change model_id
* add info about CUDA_VISIBLE_DEVICES
2025-06-21 00:01:31 +02:00
Oliver Stanley
49f3821098
add minimal verifiers example ( #472 )
2025-06-20 16:31:02 +01:00
Adefioye
9e79fc84b6
fix: Rounding issues in score_answer and add unit tests ( #462 )
2025-06-09 19:18:11 +01:00
joesharratt1229
51c2afc1fc
Fix/verl example ( #465 )
...
* updated verl ex
* updated script
* removed curriculum verl and updated
* updatied linting errors
* renamed
* updated config
2025-06-09 09:53:43 +01:00
Oliver Stanley
5726034a26
fix color_cubes answer strings, update gallery with latest envs ( #464 )
...
* update gallery with latest envs
* fix regression where answer str is wrong in color_cubes
* re-update gallery
2025-06-08 13:16:54 +02:00
Oliver Stanley
602e4be0a2
add survo env ( #461 )
...
* add survo env
* add survo curriculum
* add survo tests
2025-06-08 11:56:33 +01:00
Zafir Stojanovski
0159b1b571
Update README.md - Star History ( #463 )
2025-06-08 11:51:43 +01:00
Oliver Stanley
c2fdb11980
add kakurasu env ( #460 )
...
* add kakurasu env
* add kakurasu curriculum
* add kakurasu tests
2025-06-08 09:20:53 +01:00
Andreas Köpf
be2babea9c
Use raw URLs for images in README.md ( #459 )
...
On pypi images were not correctly rendered because the old img src urls in README.md
pointed to files on github with UI.
2025-06-06 21:23:59 +01:00
Oliver Stanley
1232a7d1e5
simplify training setup instructions ( #454 )
...
* simplify training setup instructions
* tweaks
* update cfgs
* readme update
* readme update
2025-06-06 09:51:29 +01:00
Zafir Stojanovski
0ebabf709b
Update README.md with Atropos ( #458 )
2025-06-06 09:24:25 +01:00
Zafir Stojanovski
0699e2f507
Update README.md ( #451 )
2025-06-04 12:45:23 +02:00
Oliver Stanley
1a727ecf4e
support python 3.10 ( #450 )
...
* support python 3.10
* add 3.10 to tests
* new StrEnum
2025-06-04 10:34:01 +01:00
Zafir Stojanovski
84958baa69
abs path for images ( #449 )
...
* abs path for images
* width and height outside of style
2025-06-04 10:33:13 +02:00
Oliver Stanley
2a57a95ca2
add minimal example for building training datasets ( #448 )
2025-06-03 19:28:45 +01:00
Zafir Stojanovski
b3f81a6609
fix(README): Arxiv link ( #447 )
2025-06-02 12:20:38 +02:00
Zafir Stojanovski
17a8431013
rename to easy and hard ( #445 )
2025-06-02 10:34:05 +02:00
Zafir Stojanovski
af2548f8f2
Add README assets ( #446 )
...
* add assets
* pre-commit
* remove bg
2025-06-02 10:33:54 +02:00
Adefioye
9053009dbe
Fix bug in normalize_answer method ( #444 )
2025-06-02 08:58:54 +02:00
