Papers › Divide-or-Conquer? Which Part Should You Distill Your LLM?

Divide-or-Conquer? Which Part Should You Distill Your LLM?

22 Feb 2024arXiv:2402.15000archive 2025-07-28

Zhuofeng Wu, He Bai, Aonan Zhang, Jiatao Gu, VG Vinod Vydiswaran, Navdeep Jaitly, Yizhe Zhang

Recent methods have demonstrated that Large Language Models (LLMs) can solve reasoning tasks better when they are encouraged to solve subtasks of the main task first. In this paper we devise a similar strategy that breaks down reasoning tasks into a problem decomposition phase and a problem solving phase and show that the strategy is able to outperform a single stage solution. Further, we hypothesize that the decomposition should be easier to distill into a smaller model compared to the problem solving because the latter requires large amounts of domain knowledge while the former only requires learning general problem solving strategies. We propose methods to distill these two capabilities and evaluate their impact on reasoning outcomes and inference cost. We find that we can distill the problem decomposition phase and at the same time achieve good generalization across tasks, datasets, and models. However, it is harder to distill the problem solving capability without losing performance and the resulting distilled model struggles with generalization. These results indicate that by using smaller, distilled problem decomposition models in combination with problem solving LLMs we can achieve reasoning with cost-efficient inference and local adaptation.

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 11 code samples harvested from 1 repository linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 7 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 7 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 11 samples from 1 repository, 9 ran (2 with no instrument failure; 7 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 on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

apple/ml-divide-or-conquer officialmentioned on GitHubNOASSERTIONSyntology: 11 samples, 9 ran (7 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

11 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 7 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.

7ran · our draft was wrong
2ran
2unverified

Licence: 11 of the 11 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 apple/ml-divide-or-conquer. “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.

apple/ml-divide-or-conquer official repository 11 samples, 9 ran (7 instrument-failed) · 2 unverified
add_commas evaluation/evaluation_bamb.py ran · our draft was wrong licence not identified · pointer only · d7448dc053a1ef8d · report fixture: signature number_string:str/0/str · returned str · level recorded 2026-09-24
answer_json_to_strings rejection_sampling/newselect_correct_chain_bamb.py ran · our draft was wrong licence not identified · pointer only · 5d3f431e818da5b0 · report fixture: signature answer:dict/0/? · returned tuple · level recorded 2026-09-24
completion_with_backoff run_bamb.py ran licence not identified · pointer only · d53d01a2020004ed · report fixture: signature clean_train_sen:str/0/str, backbone:str/0/str · returned str · level recorded 2026-09-24
extract_answer in 112 papers evaluation/evaluation.py ran · our draft was wrong fingerprinted licence not identified · pointer only · 2c7f4d404b0a3c5b · report fixture: signature generated:str/0/str · returned str · level recorded 2026-09-24
extract_answer in 112 papers evaluation/evaluation_bamb.py ran · our draft was wrong fingerprinted licence not identified · pointer only · 9efb8ade48dbb583 · report fixture: signature generated:str/0/str · returned str · level recorded 2026-09-24
extract_subqs rejection_sampling/newselect_correct_chain_bamb.py ran · our draft was wrong licence not identified · pointer only · 7e43b23b830e1fbb · report fixture: signature subqs:str/0/str · returned tuple · level recorded 2026-09-24
get_last_line run_gsm+drop.py ran · our draft was wrong fingerprinted licence not identified · pointer only · cd8b6cb7b70c5349 · report fixture: signature generated:str/0/str · returned str · level recorded 2026-09-24
purify_preds evaluation/evaluation_bamb.py ran fingerprinted licence not identified · pointer only · ec6139a4c80e69cb · report fixture: signature anss:str/0/str, pred:str/0/str · returned int · level recorded 2026-09-24
remove_space in 7 papers rejection_sampling/newselect_correct_chain_bamb.py ran · our draft was wrong fingerprinted licence not identified · pointer only · 4582ae4b3e09b21d · report fixture: signature q:str/0/str · returned str · level recorded 2026-09-24
ChatGPT_universal_paraphrase run_bamb.py unverified licence not identified · pointer only · 744090310d6e2276 · report
promptf run_bamb.py unverified licence not identified · pointer only · d06a7fdfa5a8b35d · report

Tasks

Problem Decomposition

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