SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.03190 · 2026

PrAg-PO: Prompt Augmented Policy Optimization for Robust and Diverse Mathematical Reasoning

Randall Balestriero, Hai Huang, Wenquan Lu, Enqi Liu

arXiv · PDF · Open in the Atlas

Code that ran

10 of 15 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 8 failures of our instrument; 5 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2602.03190.json · badge: /api/ran/2602.03190.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
wenquanlu/PrAg-PO canonical (classifier label)
classifier basis: census
10 ran · 5 no recorded run
FunctionStatusWhere it lives
apply_prime_zero_template Ran
ran; our contract draft was wrong, not the code
wenquanlu/PrAg-PO/evaluate_model.py
pointer only (licence: NONE) · get_code("bd27b7e20bc59865")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wenquanlu/PrAg-PO when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

apply_qwen_math_template Ran
ran; our contract draft was wrong, not the code
wenquanlu/PrAg-PO/evaluate_model.py
pointer only (licence: NONE) · get_code("193cf4896dff6fbb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wenquanlu/PrAg-PO when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

apply_r1_template Ran
ran; our contract draft was wrong, not the code
wenquanlu/PrAg-PO/evaluate_model.py
pointer only (licence: NONE) · get_code("05a5bcd33fb0b81f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wenquanlu/PrAg-PO when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

generate_config_from_args Ran
ran; our contract draft was wrong, not the code
wenquanlu/PrAg-PO/verl/model_merger/base_model_merger.py
pointer only (licence: NONE); the stored copy get_code serves, from LeapLabTHU/OPDVR, is pointer only (licence: NONE) · get_code("8896f4e2bafe8abc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wenquanlu/PrAg-PO when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_dynamic_pipeline_shards Ran
ran, honoured the contract we drafted
wenquanlu/PrAg-PO/verl/model_merger/megatron_model_merger.py
pointer only (licence: NONE); the stored copy get_code serves, from LeapLabTHU/OPDVR, is pointer only (licence: NONE) · get_code("94209884dcb2308e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wenquanlu/PrAg-PO when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_huggingface_actor_config Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
wenquanlu/PrAg-PO/verl/utils/model.py
pointer only (licence: NONE); the stored copy get_code serves, from Qwen-Applications/CLIPO, is pointer only (licence: NONE) · get_code("1ac72f97fbbef4f8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wenquanlu/PrAg-PO when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

normalize_final_answer Ran
ran; our contract draft was wrong, not the code
wenquanlu/PrAg-PO/understand_r1_zero/math_grader.py
pointer only (licence: NONE) · get_code("5662e5ee755b541c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wenquanlu/PrAg-PO when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

repeatness Ran
ran, violated the contract we drafted
wenquanlu/PrAg-PO/understand_r1_zero/math_grader.py
pointer only (licence: NONE) · get_code("3dcb40e5ce9bac48")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wenquanlu/PrAg-PO when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

union_tensor_dict Ran
ran; our contract draft was wrong, not the code
wenquanlu/PrAg-PO/verl/protocol.py
pointer only (licence: NONE) · get_code("21331a58f93375e4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wenquanlu/PrAg-PO when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

unpad_dataproto Ran
ran; our contract draft was wrong, not the code
wenquanlu/PrAg-PO/verl/protocol.py
pointer only (licence: NONE) · get_code("83b1686d7ac03c21")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wenquanlu/PrAg-PO when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_generation_config Not yet run
unverified (harvested, no recorded run)
wenquanlu/PrAg-PO/verl/utils/model.py
pointer only (licence: NONE); the stored copy get_code serves, from Qwen-Applications/CLIPO, is pointer only (licence: NONE) · get_code("319697b76561a1e4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wenquanlu/PrAg-PO when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_weight_loader Not yet run
unverified (harvested, no recorded run)
wenquanlu/PrAg-PO/verl/models/weight_loader_registry.py
pointer only (licence: NONE) · get_code("acf240079d434746")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wenquanlu/PrAg-PO when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_weight_saver Not yet run
unverified (harvested, no recorded run)
wenquanlu/PrAg-PO/verl/models/weight_loader_registry.py
pointer only (licence: NONE); the stored copy get_code serves, from mit-han-lab/SMEPO, is pointer only (licence: NONE) · get_code("2aeadc44472f2c85")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wenquanlu/PrAg-PO when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

mathd_normalize_answer Not yet run
unverified (harvested, no recorded run)
wenquanlu/PrAg-PO/understand_r1_zero/math_grader.py
pointer only (licence: NONE) · get_code("0388e4fa2f36659e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wenquanlu/PrAg-PO when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

squeeze Not yet run
unverified (harvested, no recorded run)
wenquanlu/PrAg-PO/verl/utils/model.py
pointer only (licence: NONE) · get_code("3b15e2ac7497c441")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wenquanlu/PrAg-PO when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 15 are also present in other papers whose code we hold (15 with at least one paper dated earlier, 12 the same month, 12 later) and 0 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
unpad_dataproto 89 other papers
36 dated earlier, 13 the same month, 37 later, 3 undated
2409.19256 (2024-09)
HybridFlow: A Flexible and Efficient RLHF Framework
2410.21236 (2024-10)
Flaming-hot Initiation with Regular Execution Sampling for Large Language Models
2025.findings-emnlp.1015 (2025 (year only))
MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learning
and 86 more not named here
squeeze 82 other papers
36 dated earlier, 12 the same month, 31 later, 3 undated
2409.19256 (2024-09)
HybridFlow: A Flexible and Efficient RLHF Framework
2410.21236 (2024-10)
Flaming-hot Initiation with Regular Execution Sampling for Large Language Models
2025.findings-emnlp.1015 (2025 (year only))
MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learning
and 79 more not named here
union_tensor_dict 64 other papers
39 dated earlier, 5 the same month, 17 later, 3 undated · 4 only as an assembly brick
2409.19256 (2024-09)
HybridFlow: A Flexible and Efficient RLHF Framework
2410.21236 (2024-10)
Flaming-hot Initiation with Regular Execution Sampling for Large Language Models
2025.findings-emnlp.1015 (2025 (year only))
MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learning
and 61 more not named here
get_generation_config 63 other papers
22 dated earlier, 10 the same month, 29 later, 2 undated
2409.19256 (2024-09)
HybridFlow: A Flexible and Efficient RLHF Framework
2410.21236 (2024-10)
Flaming-hot Initiation with Regular Execution Sampling for Large Language Models
2502.19613 (2025-02)
Self-rewarding correction for mathematical reasoning
and 60 more not named here
get_weight_loader 58 other papers
15 dated earlier, 8 the same month, 33 later, 2 undated
2409.19256 (2024-09)
HybridFlow: A Flexible and Efficient RLHF Framework
2505.14362 (2025-05)
DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning
2505.20046 (2025-05)
REARANK: Reasoning Re-ranking Agent via Reinforcement Learning
and 55 more not named here
generate_config_from_args 57 other papers
8 dated earlier, 9 the same month, 37 later, 3 undated
2410.02992 (2024-10)
Learning to Better Search with Language Models via Guided Reinforced Self-Training
2509.25787 (2025-09)
Self-Evolving Vision-Language Models for Image Quality Assessment via Voting and Ranking
2510.08630 (2025-10)
ExPO-HM: Learning to Explain-then-Detect for Hateful Meme Detection
and 54 more not named here
get_dynamic_pipeline_shards 52 other papers
7 dated earlier, 8 the same month, 35 later, 2 undated
2410.02992 (2024-10)
Learning to Better Search with Language Models via Guided Reinforced Self-Training
2509.25787 (2025-09)
Self-Evolving Vision-Language Models for Image Quality Assessment via Voting and Ranking
2510.08630 (2025-10)
ExPO-HM: Learning to Explain-then-Detect for Hateful Meme Detection
and 49 more not named here
get_huggingface_actor_config 28 other papers
2 dated earlier, 6 the same month, 19 later, 1 undated
2509.25787 (2025-09)
Self-Evolving Vision-Language Models for Image Quality Assessment via Voting and Ranking
2601.02648 (2026-01)
Prioritized Replay for RL Post-training
2602.02518 (2026-02)
GRAPHDANCER: Training LLMs to Explore and Reason over Graphs via Two-Stage Curriculum Post-Training
and 25 more not named here
mathd_normalize_answer 12 other papers
7 dated earlier, 2 the same month, 3 later
2503.10460 (2025-03)
Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond
2505.03335 (2025-05)
Absolute Zero: Reinforced Self-play Reasoning with Zero Data
2505.13379 (2025-05)
Thinkless: LLM Learns When to Think
and 9 more not named here
normalize_final_answer 9 other papers
5 dated earlier, 1 the same month, 3 later
2504.16084 (2025-04)
TTRL: Test-Time Reinforcement Learning
2509.24372 (2025-09)
Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning
2511.13223 (2025-11)
TokenSqueeze: Performance-Preserving Compression for Reasoning LLMs
and 6 more not named here
get_weight_saver 8 other papers
1 dated earlier, 3 the same month, 3 later, 1 undated
2601.05508 (2026-01)
Enabling Stroke-Level Structural Analysis of Hieroglyphic Scripts without Language-Specific Priors
2602.03143 (2026-02)
Self-Hinting Language Models Enhance Reinforcement Learning
2602.05897 (2026-02)
Stop Rewarding Hallucinated Steps: Faithfulness-Aware Step-Level Reinforcement Learning for Small Reasoning Models
and 5 more not named here
repeatness 8 other papers
4 dated earlier, 1 the same month, 3 later
2509.24372 (2025-09)
Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning
2511.13223 (2025-11)
TokenSqueeze: Performance-Preserving Compression for Reasoning LLMs
2511.15694 (2025-11)
The Impact of Quantization on Large Reasoning Model Reinforcement Learning
and 5 more not named here
apply_qwen_math_template 2 other papers
2 dated earlier
2411.01493 (2024-11)
Sample-Efficient Alignment for LLMs
2503.20783 (2025-03)
Understanding R1-Zero-Like Training: A Critical Perspective
apply_r1_template 2 other papers
2 dated earlier
2411.01493 (2024-11)
Sample-Efficient Alignment for LLMs
2503.20783 (2025-03)
Understanding R1-Zero-Like Training: A Critical Perspective
apply_prime_zero_template 1 other paper
1 dated earlier
2503.20783 (2025-03)
Understanding R1-Zero-Like Training: A Critical Perspective

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Reinforcement learning algorithms such as group-relative policy optimization (GRPO) have shown strong potential for improving the mathematical reasoning capabilities of large language models. While a growing body of work seeks to improve training entropy, rollout diversity, and exploration, most existing methods still train models with a single fixed reasoning prompt or template, which can encourage prompt-specific overfitting and unstable training dynamics. In this work, we introduce Prompt Augmented Policy Optimization (PrAg-PO), a simple policy optimization method that mixes prompt templates with templatespecific format rewards during training. By encouraging models to generate reasoning traces under diverse instructions and output formats, PrAg-PO increases rollout diversity and improves robustness. Compared with GRPO and DAPO, PrAg-PO achieves significantly higher reasoning accuracy while mitigating premature training collapse. Empirically, experiments on DeepSeek-R1-Distill-Qwen-1.5B, Qwen2.5-Math-1.5B, and Qwen3-1.7B show that PrAg-PO consistently outperforms strong baselines and achieves competitive performance against recent methods on mathematics benchmarks, using only a fixed MATH Level 3-5 training set of 8.5K problems. The code and model checkpoints are available at https://github.com/wenquanlu/PrAg-PO. Figure 1: Evaluation accuracy over training steps averaged over mathematics benchmarks for models trained on MATH Level 3-5. PrAg-PO significantly outperforms GRPO and DAPO across Qwen2.5, DeepSeek-R1-Distilled and Qwen3 models, substantially delaying the overfitting and model collapse.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2602.03190")
get_code_for_paper("2602.03190")
have("2602.03190")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2602.03190.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2602.03190.svg)](https://syntology.ai/paper/2602.03190)

Connect an agent — have() is free.