Papers › ECCO: Can We Improve Model-Generated Code Efficiency Without Sacrificing Functional...

ECCO: Can We Improve Model-Generated Code Efficiency Without Sacrificing Functional Correctness?

19 Jul 2024arXiv:2407.14044archive 2025-07-28

Siddhant Waghjale, Vishruth Veerendranath, Zora Zhiruo Wang, Daniel Fried

Although large language models (LLMs) have been largely successful in generating functionally correct programs, conditioning models to produce efficient solutions while ensuring correctness remains a challenge. Further, unreliability in benchmarking code efficiency is a hurdle across varying hardware specifications for popular interpreted languages such as Python. In this paper, we present ECCO, a reproducible benchmark for evaluating program efficiency via two paradigms: natural language (NL) based code generation and history-based code editing. On ECCO, we adapt and thoroughly investigate the three most promising existing LLM-based approaches: in-context learning, iterative refinement with execution or NL feedback, and fine-tuning conditioned on execution and editing history. While most methods degrade functional correctness and moderately increase program efficiency, we find that adding execution information often helps maintain functional correctness, and NL feedback enhances more on efficiency. We release our benchmark to support future work on LLM-based generation of efficient code.

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 harvested from 2 repositories linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 4 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: 5 samples from 1 repository, 3 ran (3 with no instrument failure; 0 where Syntology's instrument failed); found in paper text by Syntology: 9 samples from 1 repository, 7 ran (3 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 1 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

codeeff/ecco officialmentioned in paperSyntology: 5 samples, 3 ran (0 instrument-failed) · 2 unverified report
judge0/judge0 mentioned on GitHubGPL-3.0Syntology: not harvested 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

14 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 4 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.

4ran · our draft was wrong
6ran
4unverified

Licence: 5 of the 14 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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

codeeff/ecco official repository 5 samples, 3 ran (0 instrument-failed) · 2 unverified
build_coder_prompts experiments/utils.py ran no licence file found · pointer only · ffe9c8c7bc502548 · report fixture: signature row:dict/0/?, engine:MockEngine/0/?, train:bool/0/bool, few_shot:int/0/int, instruct_version:str/0/str · returned dict · level recorded 2026-09-24
build_feedback_prompts experiments/utils.py ran no licence file found · pointer only · 882b572136753409 · report fixture: signature row:dict/0/?, try_col_name:str/0/str, engine:MockEngine/0/?, train:NoneType/0/?, few_shot:int/0/int, instruct_version:str/0/str · returned dict · level recorded 2026-09-24
get_execution_feedback experiments/utils.py ran no licence file found · pointer only · 3e1be7ab52fa3b07 · report fixture: signature accept:bool/0/bool, pass_tests:list/1/int, errors:dict/0/?, run_times:dict/0/?, memory:dict/0/? · returned str · level recorded 2026-09-24
judge_eval_single_test evaluation/utils.py unverified no licence file found · pointer only · 3f906c29f0acb355 · report
judge_submit evaluation/utils.py unverified no licence file found · pointer only · 10835a1ccca19d51 · report
microsoft/DeepSpeed found in paper text by Syntology 9 samples, 7 ran (4 instrument-failed) · 2 unverified
apply_scores_before_experts_if_enabled deepspeed/module_inject/auto_ep_layer.py ran Apache-2.0 (permissive) · bc9117fa9c34b5ef · report fixture: signature routed_input:Tensor/2/float, top_scores:Tensor/1/float, score_apply:str/0/str · returned Tensor · level recorded 2026-09-24
autoep_folding_gradient_reduction_strategy deepspeed/module_inject/auto_ep_folding.py ran Apache-2.0 (permissive) · 30700c5fc6cd1064 · report fixture: signature folding_spec:ParallelFoldingSpec/0/?, param:Tensor/2/float, param_name:str/0/str · returned str · level recorded 2026-09-24
expected_folding_group_tables deepspeed/module_inject/auto_ep_folding.py ran · our draft was wrong Apache-2.0 (permissive) · ad8cfe379b811c40 · report fixture: signature spec:ParallelFoldingSpec/0/? · returned FoldingGroupTables · level recorded 2026-09-24
human_readable_size deepspeed/env_report.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 66a3320fa7fe659e · report fixture: signature size:int/0/int · returned str · level recorded 2026-09-24
local_folding_ranks deepspeed/module_inject/auto_ep_folding.py ran · our draft was wrong Apache-2.0 (permissive) · 5f8a25a43a552f16 · report fixture: signature global_rank:int/0/int, spec:ParallelFoldingSpec/0/? · returned dict · level recorded 2026-09-24
move in 8 papers deepspeed/module_inject/auto_tp.py ran Apache-2.0 (permissive) · 7a2e41bee4f05c5a · report fixture: signature tensor:Tensor/2/float, device:str/0/str, copy:bool/0/bool · returned Tensor · level recorded 2026-09-24
resolve_combine_impl deepspeed/module_inject/auto_ep_layer.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · a2da1bc94fa8af7d · report fixture: signature config_override:str/0/str · returned str · level recorded 2026-09-24
get_annotations in 13 papers deepspeed/compat.py unverified Apache-2.0 (permissive) · 45604a14e400b2f3 · report
get_annotations_from_namespace deepspeed/compat.py unverified Apache-2.0 (permissive) · 8c9ef2f97041c68b · report

Tasks

BenchmarkingCode GenerationIn-Context Learning

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