Papers › DRA-GRPO: Exploring Diversity-Aware Reward Adjustment for R1-Zero-Like Training of...

DRA-GRPO: Exploring Diversity-Aware Reward Adjustment for R1-Zero-Like Training of Large Language Models

14 May 2025arXiv:2505.09655archive 2025-07-28

Xiwen Chen, Wenhui Zhu, Peijie Qiu, Xuanzhao Dong, Hao Wang, Haiyu Wu, Huayu Li, Aristeidis Sotiras, Yalin Wang, Abolfazl Razi

Recent advances in reinforcement learning for language model post-training, such as Group Relative Policy Optimization (GRPO), have shown promise in low-resource settings. However, GRPO typically relies on solution-level and scalar reward signals that fail to capture the semantic diversity among sampled completions. This leads to what we identify as a diversity-quality inconsistency, where distinct reasoning paths may receive indistinguishable rewards. To address this limitation, we propose Diversity-aware Reward Adjustment (DRA), a method that explicitly incorporates semantic diversity into the reward computation. DRA uses Submodular Mutual Information (SMI) to downweight redundant completions and amplify rewards for diverse ones. This encourages better exploration during learning, while maintaining stable exploitation of high-quality samples. Our method integrates seamlessly with both GRPO and its variant DR.~GRPO, resulting in DRA-GRPO and DGA-DR. GRPO. We evaluate our method on five mathematical reasoning benchmarks and find that it outperforms recent strong baselines. It achieves state-of-the-art performance with an average accuracy of 58.2%, using only 7,000 fine-tuning samples and a total training cost of approximately $55. The code is available at https://github.com/xiwenc1/DRA-GRPO.

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="2505.09655")

Code

Syntology Ran 3 of 8 code samples harvested from 1 repository linked to this paper; 5 have no recorded run. Of those that ran: 3 ran with no contract checked.

By repository: official repository: 8 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

xiwenc1/dra-grpo officialmentioned in papermentioned on GitHubpytorchMIT 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

8 samples harvested; 3 ran; 0 honoured the contract we drafted; 5 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

3ran
5unverified

Licence: 0 of the 8 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 xiwenc1/dra-grpo. “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.

flatten_dict xiwenc1/dra-grpo/src/open_r1/trl/core.py official repository ran MIT (permissive) · dfd0ecd9cb25af69 · report
masked_mean xiwenc1/dra-grpo/src/open_r1/trl/core.py official repository ran fingerprinted MIT (permissive) · 4f7075aac2163cbc · report
masked_var xiwenc1/dra-grpo/src/open_r1/trl/core.py official repository ran fingerprinted MIT (permissive) · 67607956afbb2a83 · report
apply_chat_template xiwenc1/dra-grpo/src/open_r1/trl/data_utils.py official repository unverified MIT (permissive) · 53017c7a8e570221 · report
format_reward xiwenc1/dra-grpo/src/open_r1/rewards.py official repository unverified MIT (permissive) · 0a5c0b6fb53cd48c · report
is_conversational xiwenc1/dra-grpo/src/open_r1/trl/data_utils.py official repository unverified MIT (permissive) · 3c42df7a6e98e89c · report
maybe_apply_chat_template xiwenc1/dra-grpo/src/open_r1/trl/data_utils.py official repository unverified MIT (permissive) · c695ba9ac4cc3b93 · report
tag_count_reward xiwenc1/dra-grpo/src/open_r1/rewards.py official repository unverified MIT (permissive) · 0a9f60618bd16d86 · report

Tasks

DiversityMathematical Reasoning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

DRA

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