Papers › Process Reinforcement through Implicit Rewards

Process Reinforcement through Implicit Rewards

3 Feb 2025arXiv:2502.01456archive 2025-07-28

Ganqu Cui, Lifan Yuan, Zefan Wang, Hanbin Wang, Wendi Li, Bingxiang He, Yuchen Fan, Tianyu Yu, Qixin Xu, Weize Chen, Jiarui Yuan, Huayu Chen, Kaiyan Zhang, Xingtai Lv, Shuo Wang, Yuan YAO, Xu Han, Hao Peng, Yu Cheng, Zhiyuan Liu, Maosong Sun, BoWen Zhou, Ning Ding

Dense process rewards have proven a more effective alternative to the sparse outcome-level rewards in the inference-time scaling of large language models (LLMs), particularly in tasks requiring complex multi-step reasoning. While dense rewards also offer an appealing choice for the reinforcement learning (RL) of LLMs since their fine-grained rewards have the potential to address some inherent issues of outcome rewards, such as training efficiency and credit assignment, this potential remains largely unrealized. This can be primarily attributed to the challenges of training process reward models (PRMs) online, where collecting high-quality process labels is prohibitively expensive, making them particularly vulnerable to reward hacking. To address these challenges, we propose PRIME (Process Reinforcement through IMplicit rEwards), which enables online PRM updates using only policy rollouts and outcome labels through implict process rewards. PRIME combines well with various advantage functions and forgoes the dedicated reward model training phrase that existing approaches require, substantially reducing the development overhead. We demonstrate PRIME's effectiveness on competitional math and coding. Starting from Qwen2.5-Math-7B-Base, PRIME achieves a 15.1% average improvement across several key reasoning benchmarks over the SFT model. Notably, our resulting model, Eurus-2-7B-PRIME, surpasses Qwen2.5-Math-7B-Instruct on seven reasoning benchmarks with 10% of its training data.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 17 code samples harvested from 1 repository linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 17 samples from 1 repository, 14 ran (10 with no instrument failure; 4 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 3 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

prime-rl/prime officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 17 samples, 14 ran (4 instrument-failed) · 3 unverified report
OpenLLMAI/OpenLLaMA2 mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning (arXiv:2502.14768; that paper's own run record: 15 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 8 unverified); nothing checks that they implement this paper's method. report
OpenLLMAI/OpenRLHF mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
cjreinforce/pure mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning (arXiv:2504.15275; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
openrlhf/openrlhf mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A Regret Minimization Framework on Preference Learning in Large Language Models (arXiv:2606.09124; that paper's own run record: 15 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 8 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

17 samples harvested: 14 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
4ran · our draft was wrong
8ran
3unverified

Licence: 2 of the 17 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from prime-rl/prime. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

prime-rl/prime official repository 17 samples, 14 ran (4 instrument-failed) · 3 unverified
create_filter_prompt data_preprocessing/stage2_format_choice.py ran Apache-2.0 (permissive) · 4af93356397e2583 · report fixture: signature item:dict/0/? · returned list · level recorded 2026-09-24
create_question_prompt data_preprocessing/stage2_format_choice.py ran Apache-2.0 (permissive) · c7721490607b846e · report fixture: signature item:dict/0/? · returned list · level recorded 2026-09-24
create_solution_prompt data_preprocessing/stage2_format_choice.py ran Apache-2.0 (permissive) · 120a553951e00af6 · report fixture: signature item:dict/0/? · returned list · level recorded 2026-09-24
estimate_pass_at_k in 28 papers eval/utils/evaluation.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · e080db2eaa81fdb3 · report fixture: signature num_samples:int/0/int, num_correct:ndarray/1/int, k:int/0/int · returned ndarray · level recorded 2026-09-22
handle_base in 6 papers data_preprocessing/math_util/grader.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · bb175bff1060d928 · report fixture: signature x:str/0/str · returned int · level recorded 2026-09-26
is_digit in 33 papers data_preprocessing/math_util/grader.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 2a180d3156997924 · report fixture: signature s:str/0/str · returned tuple · level recorded 2026-09-26
normalize in 638 papers
census: 70 implementations from 82 papers, 51 distinct outputs across 11 buckets, one shared input per bucket
data_preprocessing/math_util/grader.py ran · our draft was wrong Apache-2.0 (permissive) · 960059cee2753e3f · report fixture: signature answer:str/0/str, pi:float/0/float · returned str · level recorded 2026-09-26
normalize_answer in 304 papers data_preprocessing/math_util/math_normalize.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 101b1e54fcdadf90 · report fixture: signature answer:str/0/str · returned str · level recorded 2026-09-24
parallel_evaluate_continual_async training/verl/utils/reward_score/prime.py ran Apache-2.0 (permissive) · 2f2aa5fc73311d4e · report fixture: returned coroutine · level recorded 2026-09-24
process_humaneval_test eval/utils/evaluation_leetcode.py ran Apache-2.0 (permissive) · af48c07b88855b2d · report fixture: signature sample:dict/0/?, problems:dict/0/?, example_test:bool/0/bool, is_mbpp:bool/0/bool, language:str/0/str · returned str · level recorded 2026-09-26
process_row_with_timeout training/verl/utils/reward_score/prime.py ran Apache-2.0 (permissive) · 38c21e0e3a1e76d2 · report fixture: signature completion:str/0/str, reference:int/0/int, task:str/0/str, executor:ThreadPoolExecutor/0/?, timeout:float/0/float · returned coroutine · level recorded 2026-09-25
read_problems in 17 papers eval/utils/data.py ran · our draft was wrong Apache-2.0 (permissive) · 562c0ef13357b53b · report fixture: returned dict · level recorded 2026-09-26
tell_choice data_preprocessing/stage1_filter.py ran Apache-2.0 (permissive) · 860555756a95114b · report fixture: signature d:dict/0/?, extracted_model_output:NoneType/0/? · returned bool · level recorded 2026-09-25
tell_choice data_preprocessing/stage3_merge.py ran Apache-2.0 (permissive) · 652e9a2cd5d2bd69 · report fixture: signature d:dict/0/? · returned bool · level recorded 2026-09-25
process_completion training/verl/utils/reward_score/prime.py unverified Apache-2.0 (permissive) · aacfe469bd668c58 · report
process_fn in 5 papers data_preprocessing/stage1_filter.py unverified Apache-2.0 (permissive) · 86bc2b52fc4de062 · report
process_fn in 5 papers data_preprocessing/stage3_merge.py unverified Apache-2.0 (permissive) · 4dc6b4c66100580d · report

Tasks

MathReinforcement Learning (RL)

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SFT

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