Commit graph

82 commits

Author SHA1 Message Date
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
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
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
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
47303211b3
update gallery (#434) 2025-05-15 22:41:43 +02:00
Andreas Köpf
7853263650
bump dev version to 0.1.19 2025-04-03 22:19:07 +01:00
Andreas Köpf
d2c895f1d3
Refactor Curriculum Attributes (#335)
* remove min_value from AttributeDefinition
* remove type from AttributeDefinition
* Add CurriculumContext
* add ensure_interval option for RangeAttributes
* docs: Add legend explaining curriculum indicators in dataset gallery
* update GALLERY.md
2025-03-16 15:40:28 +01:00
Andreas Koepf
79ba55aae3 update gallery 2025-03-14 16:18:43 +01:00
Andreas Koepf
1b004bf888 bump version 2025-03-10 00:32:57 +01:00
Andreas Koepf
fb06038e88 update gallery 2025-03-07 16:24:47 +01:00
Andreas Koepf
862617b7e0 update gallery, pypi release, bump version 2025-03-05 23:45:45 +01:00
Andreas Koepf
b5742de5e5 update gallery 2025-02-26 18:23:06 +01:00
Andreas Koepf
b5f6f7d753 bump version, update gallery 2025-02-23 22:36:39 +01:00
Andreas Koepf
97b30f5f53 update GALLERY.md 2025-02-21 17:30:33 +01:00
Andreas Koepf
f1daa8d1da update GALLERY.my, bump version 2025-02-20 23:03:54 +01:00
Andreas Koepf
4201c7a9b0 update GALLERY.md 2025-02-19 22:45:50 +01:00
Andreas Koepf
2cbaab2918 fix question templates 2025-02-16 23:04:24 +01:00
Andreas Koepf
f1bd5ef493 import FutoshikiDataset & update GALLERY 2025-02-15 21:26:15 +01:00
Andreas Koepf
f7e928711e bump version, update GALLERY.md 2025-02-14 23:34:59 +01:00
Andreas Koepf
5d16a2193c import string_insertion, minor whitespace fixes, gallery update 2025-02-14 07:55:38 +01:00
Andreas Koepf
56ba500959 update GALLERY.md & bump version 2025-02-11 23:43:56 +01:00
Andreas Koepf
4abcd1f1df update gallery, lower default config values for PowerFunctionDataset 2025-02-10 22:42:04 +01:00
Andreas Koepf
8c4400b18a reduce default zero probability for binary matrix 2025-02-09 20:05:56 +01:00
Andreas Koepf
72b37eba5a update GALLERY.md after merging knight_swap 2025-02-09 00:35:56 +01:00
Andreas Köpf
8132cd6d90
Merge pull request #89 from JeanKaddour/feat-swap-knights-puzzles
Feat swap knights puzzles
2025-02-09 00:33:48 +01:00
Andreas Koepf (aider)
3137e0f433 feat: Add configurable rotation and mirror augmentation variants 2025-02-09 00:16:41 +01:00
Andreas Koepf
60effc6e7a move arc_1d into from cognition into arc folder 2025-02-08 19:37:26 +01:00
Andreas Koepf
f562737eef update gallery spiral_matrix 2025-02-08 19:15:26 +01:00
Andreas Köpf
28e3545cf9
Merge pull request #85 from zafstojano/env/spiral-matrix
Spiral Matrix
2025-02-08 19:14:02 +01:00
Andreas Koepf
63cbb8722d remove unnecessary newline from arc prompt 2025-02-08 19:12:41 +01:00
Andreas Koepf
d0ee809757 re-arc cleanup 2025-02-08 19:07:28 +01:00
Zafir Stojanovski
3f5cfeed95 Merge branch 'main' of https://github.com/open-thought/reasoning-gym into env/spiral-matrix 2025-02-08 18:52:45 +01:00
Andreas Köpf
f8449b2e1a
Merge branch 'main' into env/ransom-note 2025-02-08 17:34:31 +01:00
Jean Kaddour
689251b3bb
Update GALLERY.md to include Knight Swap 2025-02-08 15:49:10 +00:00
Andreas Koepf
f2e02d6d08 add CONTRIBUTING.md, simplify README.md 2025-02-08 15:59:44 +01:00
Zafir Stojanovski
2d57efa07a remove GALLERY.md stuff 2025-02-08 14:50:54 +01:00
Zafir Stojanovski
49587a9a63 remove GALLERY.md stuff 2025-02-08 14:50:06 +01:00
Zafir Stojanovski
b8cc814e7f Merge branch 'main' of https://github.com/open-thought/reasoning-gym into env/ransom-note 2025-02-08 13:19:37 +01:00
Zafir Stojanovski
3fbfa82afb Merge branch 'main' of https://github.com/open-thought/reasoning-gym into env/spiral-matrix 2025-02-08 13:15:02 +01:00
Jean Kaddour
8e02b363c1
Update GALLERY.md 2025-02-08 08:26:25 +00:00
Jean Kaddour
a2515ad9c7 make formatting consistent 2025-02-07 23:07:29 +00:00
Jean Kaddour
64b96b5fff refactor: add more docstrings and examples to tsumego 2025-02-07 23:02:57 +00:00
Andreas Koepf
d3752a0d76 bump version to 0.1.14 2025-02-07 18:28:06 +01:00
Andreas Koepf
848997ee47 add complex_arithmetic 2025-02-07 17:53:30 +01:00
Andreas Koepf
81cb7aa42b Add GO hints, legend, disallow numeric answer, store expected string answer 2025-02-07 15:20:00 +01:00
Zafir Stojanovski
b24da41e69 ransom note 2025-02-07 14:47:00 +01:00
Zafir Stojanovski
0a20a2e582 spiral matrix 2025-02-07 12:46:36 +01:00
Andreas Köpf
426fa22fcc
Sokoban without pygame (#77)
* add minified version of https://github.com/xbandrade/sokoban-solver-generator

---------

Co-authored-by: Rich Jones <miserlou@gmail.com>
2025-02-07 11:57:53 +01:00
Andreas Köpf
d2bef8d30f
Merge pull request #65 from zafstojano/env/group-anagrams
Group Anagrams together
2025-02-06 13:03:27 +01:00