SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2601.14716 · 2026

PCL-Reasoner-V1.5: Advancing Math Reasoning with Offline Reinforcement Learning

Bin Zhou, Jie Chen, Yonghong Tian, Yao Lu, Fan Xu, Dengdong Fan, Jianzheng Nie

arXiv · PDF · Open in the Atlas

Code that ran

3 of 6 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, 0 violated it and 0 have no contract verdict; 2 failures of our instrument; 3 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/2601.14716.json · badge: /api/ran/2601.14716.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
PCL-Reasoner/V1.5 canonical (classifier label)
classifier basis: census
3 ran · 3 no recorded run
FunctionStatusWhere it lives
cut_range_to_subs Ran
ran, honoured the contract we drafted
PCL-Reasoner/V1.5/MindSpeed-LLM/preprocess_data.py
pointer only (licence: NONE) · get_code("897e7d57f65220cf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PCL-Reasoner/V1.5 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.

find_parquet_files Ran
ran; our contract draft was wrong, not the code
PCL-Reasoner/V1.5/data_preprocess/convert_parquet2jsonl.py
pointer only (licence: NONE) · get_code("3c8f6555818d3406")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PCL-Reasoner/V1.5 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.

process_single_file Ran
ran; our contract draft was wrong, not the code
PCL-Reasoner/V1.5/data_preprocess/convert_parquet2jsonl.py
pointer only (licence: NONE) · get_code("5da0c82bf1c067c5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PCL-Reasoner/V1.5 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_result Not yet run
unverified (harvested, no recorded run)
PCL-Reasoner/V1.5/MindSpeed-LLM/evaluation.py
pointer only (licence: NONE) · get_code("ebe7ee2f07cfd847")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PCL-Reasoner/V1.5 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.

load_plugin Not yet run
unverified (harvested, no recorded run)
PCL-Reasoner/V1.5/MindSpeed-LLM/convert_ckpt.py
pointer only (licence: NONE) · get_code("a19f11fd8890cc88")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PCL-Reasoner/V1.5 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.

process_files_parallel Not yet run
unverified (harvested, no recorded run)
PCL-Reasoner/V1.5/data_preprocess/convert_parquet2jsonl.py
pointer only (licence: NONE) · get_code("056a456d8855da31")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PCL-Reasoner/V1.5 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 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 6 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.

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

We present PCL-Reasoner-V1.5, a 32-billion-parameter large language model (LLM) for mathematical reasoning. The model is built upon Qwen2.5-32B and refined via supervised fine-tuning (SFT) followed by reinforcement learning (RL). A central innovation is our proposed offline RL method, which provides superior training stability and efficiency over standard online RL methods such as GRPO. Our model achieves state-of-the-art performance among models post-trained on Qwen2.5-32B, attaining average accuracies of 90.9% on AIME 2024 and 85.6% on AIME 2025. Our work demonstrates offline RL as a stable and efficient paradigm for advancing reasoning in LLMs. All experiments were conducted on Huawei Ascend 910C NPUs.

For agents

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

get_harvested_code_for_paper("2601.14716")
get_code_for_paper("2601.14716")
have("2601.14716")

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

curl https://syntology.ai/api/ran/2601.14716.json

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

[![Syntology run record](https://syntology.ai/api/ran/2601.14716.svg)](https://syntology.ai/paper/2601.14716)

Connect an agent — have() is free.