Papers › ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning...

ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models

16 Oct 2023arXiv:2310.10505archive 2025-07-28

Ziniu Li, Tian Xu, Yushun Zhang, Zhihang Lin, Yang Yu, Ruoyu Sun, Zhi-Quan Luo

Reinforcement Learning from Human Feedback (RLHF) is key to aligning Large Language Models (LLMs), typically paired with the Proximal Policy Optimization (PPO) algorithm. While PPO is a powerful method designed for general reinforcement learning tasks, it is overly sophisticated for LLMs, leading to laborious hyper-parameter tuning and significant computation burdens. To make RLHF efficient, we present ReMax, which leverages 3 properties of RLHF: fast simulation, deterministic transitions, and trajectory-level rewards. These properties are not exploited in PPO, making it less suitable for RLHF. Building on the renowned REINFORCE algorithm, ReMax does not require training an additional value model as in PPO and is further enhanced with a new variance reduction technique. ReMax offers several benefits over PPO: it is simpler to implement, eliminates more than 4 hyper-parameters in PPO, reduces GPU memory usage, and shortens training time. ReMax can save about 46% GPU memory than PPO when training a 7B model and enables training on A800-80GB GPUs without the memory-saving offloading technique needed by PPO. Applying ReMax to a Mistral-7B model resulted in a 94.78% win rate on the AlpacaEval leaderboard and a 7.739 score on MT-bench, setting a new SOTA for open-source 7B models. These results show the effectiveness of ReMax while addressing the limitations of PPO in LLMs.

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 13 code samples harvested from 1 repository linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 13 samples from 1 repository, 11 ran (9 with no instrument failure; 2 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 2 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.

liziniu/ReMax officialmentioned in papermentioned on GitHubpytorchSyntology: 13 samples, 11 ran (2 instrument-failed) · 2 unverified report
niutrans/gram mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to GRAM: A Generative Foundation Reward Model for Reward Generalization (arXiv:2506.14175; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
openpsi-project/realhf mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models (arXiv:2402.03300; that paper's own run record: 14 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 11 where Syntology's instrument failed) · 10 unverified) and SimPO: Simple Preference Optimization with a Reference-Free Reward (arXiv:2405.14734; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 0 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

13 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 2 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.

1ran · honoured contract
1ran · our draft was wrong
1ran; the contract check could not run
8ran
2unverified

Licence: 13 of the 13 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 liziniu/ReMax. “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.

liziniu/ReMax official repository 13 samples, 11 ran (2 instrument-failed) · 2 unverified
calculate_flops in 10 papers utils/perf.py ran no licence file found · pointer only · 069f56cb00324e10 · report fixture: signature checkpoint_activations_factor:float/0/float, batch_size:int/0/int, seq_length:int/0/int, hf_config:HFConfig/0/? · returned float · level recorded 2026-09-26
gather_log_probs in 12 papers step3_rlhf_finetuning/remax_trainer.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only · 2f0a690c70d11c23 · report fixture: signature logits:Tensor/2/float, labels:Tensor/1/int · returned Tensor · level recorded 2026-09-22
generate in 143 papers
census: 5 implementations from 6 papers, 5 distinct outputs across 4 buckets, one shared input per bucket
step1_supervised_finetuning/prompt_eval.py ran no licence file found · pointer only · 56842aca28dc25b7 · report fixture: signature model:callable/0/?, tokenizer:MinimalTokenizer/0/?, inputs:Inputs/0/?, num_beams:int/0/int, num_beam_groups:int/0/int, do_sample:bool/0/bool, num_return_sequences:int/0/int, max_new_tokens:int/0/int · returned list · level recorded 2026-09-24
generate_constrastive_search in 5 papers step1_supervised_finetuning/prompt_eval.py ran no licence file found · pointer only · 385922750eb70702 · report fixture: signature model:callable/0/?, tokenizer:StandInTokenizer/0/?, inputs:StandInInputs/0/?, top_k:int/0/int, penalty_alpha:float/0/float, num_return_sequences:int/0/int, max_new_tokens:int/0/int · returned list · level recorded 2026-09-24
get_eval_ds_config in 20 papers utils/ds_utils.py ran no licence file found · pointer only · e221a76f7d7a3d73 · report fixture: signature offload:bool/0/bool, stage:int/0/int, bf16:bool/0/bool, memory_efficient_linear:bool/0/bool · returned dict · level recorded 2026-09-24
get_hf_configs in 7 papers utils/perf.py ran · honoured contract no licence file found · pointer only · df20c2f4083d17af · report fixture: signature hf_config:MockHFConfig/0/? · returned tuple · level recorded 2026-09-26
log_init in 10 papers step3_rlhf_finetuning/rlhf_engine.py ran no licence file found · pointer only · 429d42a3bf925da5 · report fixture: signature model_name:str/0/str, stime:NoneType/0/? · returned float · level recorded 2026-09-26
only_optimize_lora_parameters in 10 papers utils/module/lora.py ran · our draft was wrong no licence file found · pointer only · e617041853afd002 · report fixture: signature model:callable/0/? · returned LoRAModel · level recorded 2026-09-24
prepare_datapair in 5 papers step2_reward_model_finetuning/rw_eval.py ran no licence file found · pointer only · ed8922a081978462 · report fixture: signature prompt:str/0/str, good_ans:str/0/str, bad_ans:str/0/str, tokenizer:callable/0/?, max_seq_len:int/0/int, end_of_conversation_token:str/0/str · returned dict · level recorded 2026-09-24
prepare_singlesample in 5 papers step2_reward_model_finetuning/rw_eval.py ran no licence file found · pointer only · 779ea48e220986c3 · report fixture: signature prompt:str/0/str, good_ans:str/0/str, tokenizer:callable/0/?, max_seq_len:int/0/int, end_of_conversation_token:str/0/str · returned dict · level recorded 2026-09-24
to_device in 75 papers utils/utils.py ran no licence file found · pointer only · 07ef4eb19492501f · report fixture: signature batch:dict/0/?, device:device/0/? · returned dict · level recorded 2026-09-24
get_tokenizer in 156 papers utils/utils.py unverified no licence file found · pointer only · d0bac507b6ee8862 · report
load_hf_tokenizer in 10 papers utils/utils.py unverified no licence file found · pointer only · 88cecd279a8c1dff · report

Tasks

General Reinforcement Learningreinforcement-learning

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Entropy RegularizationPPOREINFORCEZeRO

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