Papers › Efficient Reinforcement Finetuning via Adaptive Curriculum Learning

Efficient Reinforcement Finetuning via Adaptive Curriculum Learning

7 Apr 2025arXiv:2504.05520archive 2025-07-28

Taiwei Shi, Yiyang Wu, Linxin Song, Tianyi Zhou, Jieyu Zhao

Reinforcement finetuning (RFT) has shown great potential for enhancing the mathematical reasoning capabilities of large language models (LLMs), but it is often sample- and compute-inefficient, requiring extensive training. In this work, we introduce AdaRFT (Adaptive Curriculum Reinforcement Finetuning), a method that significantly improves both the efficiency and final accuracy of RFT through adaptive curriculum learning. AdaRFT dynamically adjusts the difficulty of training problems based on the model's recent reward signals, ensuring that the model consistently trains on tasks that are challenging but solvable. This adaptive sampling strategy accelerates learning by maintaining an optimal difficulty range, avoiding wasted computation on problems that are too easy or too hard. AdaRFT requires only a lightweight extension to standard RFT algorithms like Proximal Policy Optimization (PPO), without modifying the reward function or model architecture. Experiments on competition-level math datasets-including AMC, AIME, and IMO-style problems-demonstrate that AdaRFT significantly improves both training efficiency and reasoning performance. We evaluate AdaRFT across multiple data distributions and model sizes, showing that it reduces training time by up to 2x and improves accuracy by a considerable margin, offering a more scalable and effective RFT framework.

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 15 code samples harvested from 1 repository linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 3 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: 15 samples from 1 repository, 9 ran (5 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.

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. 2 of the 9 samples that ran have no recorded date.

uscnlp-lime/verl officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 15 samples, 9 ran (4 instrument-failed) · 6 unverified 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

15 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 6 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 · violated contract
3ran · our draft was wrong
1ran; the contract check could not run
3ran
6unverified

Licence: 3 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 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 uscnlp-lime/verl. “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.

uscnlp-lime/verl official repository 15 samples, 9 ran (4 instrument-failed) · 6 unverified
convert_to_regular_types in 9 papers verl/trainer/fsdp_sft_trainer.py ran · our draft was wrong Apache-2.0 (permissive) · f887d72c9492d9ee · report fixture: signature obj:DictConfig/0/? · returned dict · level recorded, date not recorded
extract_step in 22 papers verl/trainer/fsdp_sft_trainer.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 216e28c040173a61 · report fixture: signature path:str/0/str · returned int · level recorded, date not recorded
get_huggingface_actor_config in 83 papers verl/utils/model.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · fe79c459a3e4cc64 · report fixture: signature model_name:str/0/str, override_config_kwargs:dict/0/?, trust_remote_code:bool/0/bool · returned MockConfig · level recorded 2026-09-25
get_rope_index in 11 papers verl/models/transformers/qwen2_vl.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · e29ba2dcd05add9f · report fixture: signature processor:MockProcessor/0/?, input_ids:Tensor/1/int, image_grid_thw:Tensor/2/int, video_grid_thw:Tensor/2/int, second_per_grid_ts:Tensor/1/float, attention_mask:Tensor/1/int · returned Tensor · level recorded 2026-09-26
is_transformers_version_in_range in 15 papers verl/models/transformers/monkey_patch.py ran · violated contract Apache-2.0 (permissive) · 42a7954a8cfa89e0 · report fixture: signature min_version:str/0/str, max_version:str/0/str · returned bool · level recorded 2026-09-24
prepare_fa2_from_position_ids in 15 papers verl/models/transformers/qwen2_vl.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · e89bd73550a8c08f · report fixture: signature query:Tensor/3/float, key:Tensor/3/float, value:Tensor/3/float, position_ids:Tensor/2/int · returned tuple · level recorded 2026-09-26
repeat_kv in 244 papers
census: 15 implementations from 60 papers, 2 distinct outputs on one shared input
verl/models/transformers/monkey_patch.py ran fingerprinted Apache-2.0 (permissive) · 00f0f9848c8cd16c · report fixture: signature hidden_states:Tensor/4/float, n_rep:int/0/int · returned Tensor · level recorded 2026-09-25
union_tensor_dict in 69 papers verl/protocol.py ran · our draft was wrong Apache-2.0 (permissive) · 21331a58f93375e4 · report fixture: signature tensor_dict1:TensorDict/1/float, tensor_dict2:TensorDict/1/float · returned TensorDict · level recorded 2026-09-22
unpad_dataproto in 102 papers verl/protocol.py ran · our draft was wrong Apache-2.0 (permissive) · 25f0ea3f460f6ce1 · report fixture: signature data:DataProto/0/?, pad_size:int/0/int · returned DataProto · level recorded 2026-09-22
flash_attention_forward in 14 papers verl/models/transformers/qwen2_vl.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · 736144d442549c26 · report
get_generation_config in 66 papers verl/utils/model.py unverified Apache-2.0 (permissive) · 660713a8fa047736 · report
get_weight_loader in 93 papers verl/models/weight_loader_registry.py unverified Apache-2.0 (permissive) · 39fba8c5b01d595e · report
get_weight_saver in 69 papers verl/models/weight_loader_registry.py unverified Apache-2.0 (permissive) · 8bf1b3e9bf87072c · report
load_state_dict_to_megatron_gptmodel in 7 papers verl/models/mcore/loader.py unverified Apache-2.0 (permissive) · 1901b047ab8e1654 · report
squeeze in 92 papers verl/utils/model.py unverified Apache-2.0 (permissive) · 3b15e2ac7497c441 · report

Tasks

MathMathematical Reasoning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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