Papers › Concise Reasoning via Reinforcement Learning

Concise Reasoning via Reinforcement Learning

7 Apr 2025arXiv:2504.05185archive 2025-07-28

Mehdi Fatemi, Banafsheh Rafiee, Mingjie Tang, Kartik Talamadupula

Despite significant advancements in large language models (LLMs), a major drawback of reasoning models is their enormous token usage, which increases computational cost, resource requirements, and response time. In this work, we revisit the core principles of reinforcement learning (RL) and, through mathematical analysis, demonstrate that the tendency to generate lengthy responses arises inherently from RL-based optimization during training. This finding questions the prevailing assumption that longer responses inherently improve reasoning accuracy. Instead, we uncover a natural correlation between conciseness and accuracy that has been largely overlooked. We show that introducing a secondary phase of RL training, using a very small set of problems, can significantly reduce chains of thought while maintaining or even enhancing accuracy. Additionally, we demonstrate that, while GRPO shares some interesting properties of PPO, it suffers from collapse modes, which limit its reliability for concise reasoning. Finally, we validate our conclusions through extensive experimental results.

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 14 code samples: 13 from 1 repository linked to this paper, 1 identical to code harvested from another paper's repository. Across all 14: 12 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 5 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 13 samples from 1 repository, 11 ran (6 with no instrument failure; 5 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. 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 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

ai-wand/concise-reasoning officialmentioned in papermentioned on GitHubpytorchMITSyntology: 13 samples, 11 ran (5 instrument-failed) · 2 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

14 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 5 violated, 0 with no contract checked; 6 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
5ran · violated contract
6ran · our draft was wrong
2unverified

Licence: 13 of the 14 samples are pointer only, meaning Syntology does not serve that copy's text. For 12 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 ai-wand/concise-reasoning. 1 sample is listed last, in a group without a repository. “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.

ai-wand/concise-reasoning official repository 13 samples, 11 ran (5 instrument-failed) · 2 unverified
choice_answer_clean in 17 papers eval/grader.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 809c0178a7ae90ff · report fixture: signature pred:str/0/str · returned str · level recorded 2026-09-25
compare_numerical_ans in 7 papers eval/math_utils.py ran · violated contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 81082f28e1440f9d · report fixture: signature ans_p:str/0/str, ans_l:str/0/str · returned bool · level recorded 2026-09-25
extract_multi_choice_answer in 13 papers eval/parser.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · ed2f4689128f9885 · report fixture: signature pred_str:str/0/str · returned str · level recorded 2026-09-25
generate_completions in 38 papers eval/model_utils.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 1525d8bc0fc8d5a0 · report fixture: signature model:callable/0/?, tokenizer:callable/0/?, prompts:list/1/str, batch_size:int/0/int, stop_id_sequences:list/1/str, add_special_tokens:bool/0/bool, disable_tqdm:bool/0/bool, max_length:int/0/int, num_return_sequences:int/0/int · returned list · level recorded 2026-09-24
is_digit in 33 papers eval/grader.py ran · violated contract MIT (permissive) here; the stored copy is pointer only · fb37d3c84b18e368 · report fixture: signature num:str/0/str · returned bool · level recorded 2026-09-25
is_execution_success eval/trajectory.py ran · violated contract MIT (permissive) here; the stored copy is pointer only · 581f3949cfdcffa2 · report fixture: signature output:str/0/str · returned bool · level recorded 2026-09-25
is_multi_choice in 9 papers eval/math_eval.py ran · violated contract MIT (permissive) · d338a8cb44aeb6b4 · report fixture: signature answer:str/0/str · returned bool · level recorded 2026-09-22
is_number in 70 papers eval/math_utils.py ran · violated contract MIT (permissive) here; the stored copy is pointer only · 1c1060f6e43d5dfa · report fixture: signature element:str/0/str · returned bool · level recorded 2026-09-25
parse_digits in 20 papers eval/grader.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 7d4b7f8c3875b126 · report fixture: signature num:str/0/str · returned float · level recorded 2026-09-25
text_to_trajectory eval/trajectory.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 7e48538d19cc0d8f · report fixture: signature traj_str:str/0/str · returned list · level recorded 2026-09-25
trajectory_to_text eval/trajectory.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 0d7ae684ec6c7537 · report fixture: signature trajectory:list/1/dict · returned str · level recorded 2026-09-25
load_hf_lm_and_tokenizer in 21 papers eval/model_utils.py unverified MIT (permissive) here; the stored copy is pointer only · ee71a94d9dd1b8e9 · report
my_parse_latex in 7 papers eval/math_utils.py unverified MIT (permissive) here; the stored copy is pointer only · 73925940858a62b3 · report
Repository not located 1 sample, 1 ran (1 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
reward_fn in 7 papers repository not located ran · our draft was wrong licence of this copy not recorded · 18ed61dcfadbbdf0 · report fixture: signature rewards:list/1/Tensor · returned Tensor · level recorded 2026-09-22

Tasks

Reinforcement LearningReinforcement Learning (RL)reinforcement-learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Entropy RegularizationPPOSET

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