Papers › Self-Explore: Enhancing Mathematical Reasoning in Language Models with Fine-grained Rewards

Self-Explore: Enhancing Mathematical Reasoning in Language Models with Fine-grained Rewards

16 Apr 2024arXiv:2404.10346archive 2025-07-28

Hyeonbin Hwang, Doyoung Kim, Seungone Kim, Seonghyeon Ye, Minjoon Seo

Training on large amounts of rationales (i.e., CoT Fine-tuning) is effective at improving the reasoning capabilities of large language models (LLMs). However, acquiring human-authored rationales or augmenting rationales from proprietary models is costly and not scalable. In this paper, we study the problem of whether LLMs could self-improve their reasoning capabilities. To this end, we propose Self-Explore, where the LLM is tasked to explore the first wrong step (i.e., the first pit) within the rationale and use such signals as fine-grained rewards for further improvement. On the GSM8K and MATH test set, Self-Explore achieves 11.57% and 2.89% improvement on average across three LLMs compared to supervised fine-tuning (SFT). Our code is available at https://github.com/hbin0701/Self-Explore.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2404.10346")

Code

Syntology Ran 8 of 9 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 1 ran · our draft was wrong; 7 ran with no contract checked.

By repository: official repository: 8 samples from 1 repository, 7 ran; 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

hbin0701/Self-Explore officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

9 samples harvested; 8 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
7ran
1unverified

Licence: 9 of the 9 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from hbin0701/Self-Explore. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

check_equation hbin0701/Self-Explore/gen/get_rft_data.py official repository ran no licence file found · pointer only · 771d0d0c6a85a612 · report
extract_answer hbin0701/Self-Explore/gen/utils_others.py official repository ran fingerprinted no licence file found · pointer only · 50408bcb3e87455b · report
extract_answers hbin0701/Self-Explore/gen/utils_others.py official repository ran no licence file found · pointer only · fc107f0a7cb2bb77 · report
get_dataset hbin0701/Self-Explore/dpo/prepare_dataset.py official repository ran no licence file found · pointer only · 48f4dfa28740b7de · report
is_eq_correct hbin0701/Self-Explore/gen/get_rft_data.py official repository ran no licence file found · pointer only · f3a68206b24244ce · report
read_jsonl hbin0701/Self-Explore/gen/get_rft_data.py official repository ran no licence file found · pointer only · c4783f2528e590ab · report
standardize_value_str hbin0701/Self-Explore/gen/utils_others.py official repository ran fingerprinted no licence file found · pointer only · f5c2fbf1177f0d1f · report
get_quantization_config hbin0701/Self-Explore/dpo/alignment/model_utils.py official repository unverified no licence file found · pointer only · 0ad5c5d201bc2f1e · report
batch_data identical code first harvested elsewhere ran · our draft was wrong fingerprinted licence of this copy not recorded · 66b3b5450182da3a · report

Tasks

GSM8KMathMathematical Reasoning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections