Papers › DARG: Dynamic Evaluation of Large Language Models via Adaptive Reasoning Graph

DARG: Dynamic Evaluation of Large Language Models via Adaptive Reasoning Graph

25 Jun 2024arXiv:2406.17271archive 2025-07-28

Zhehao Zhang, Jiaao Chen, Diyi Yang

The current paradigm of evaluating Large Language Models (LLMs) through static benchmarks comes with significant limitations, such as vulnerability to data contamination and a lack of adaptability to the evolving capabilities of LLMs. Therefore, evaluation methods that can adapt and generate evaluation data with controlled complexity are urgently needed. In this work, we introduce Dynamic Evaluation of LLMs via Adaptive Reasoning Graph Evolvement (DARG) to dynamically extend current benchmarks with controlled complexity and diversity. Specifically, we first extract the reasoning graphs of data points in current benchmarks and then perturb the reasoning graphs to generate novel testing data. Such newly generated test samples can have different levels of complexity while maintaining linguistic diversity similar to the original benchmarks. We further use a code-augmented LLM to ensure the label correctness of newly generated data. We apply our DARG framework to diverse reasoning tasks in four domains with 15 state-of-the-art LLMs. Experimental results show that almost all LLMs experience a performance decrease with increased complexity and certain LLMs exhibit significant drops. Additionally, we find that LLMs exhibit more biases when being evaluated via the data generated by DARG with higher complexity levels. These observations provide useful insights into how to dynamically and adaptively evaluate LLMs. The code is available at https://github.com/SALT-NLP/DARG.

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 12 code samples harvested from 1 repository linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 2 violated, 4 with no contract checked; 6 where Syntology's instrument failed) · 0 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: 12 samples from 1 repository, 12 ran (6 with no instrument failure; 6 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.

salt-nlp/darg officialmentioned in papermentioned on GitHubSyntology: 12 samples, 12 ran (6 instrument-failed) · 0 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

12 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 2 violated, 4 with no contract checked; 6 where Syntology's instrument failed) · 0 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.

2ran · violated contract
6ran · our draft was wrong
4ran

Licence: 12 of the 12 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 salt-nlp/darg. “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.

salt-nlp/darg official repository 12 samples, 12 ran (6 instrument-failed) · 0 unverified
check_direct_person_to_label_connection BBQ/bbq_graph_construct.py ran · violated contract no licence file found · pointer only · e9c164fc3e446d20 · report fixture: signature graph:dict/0/? · returned bool · level recorded 2026-09-24
check_person_attribute_connections BBQ/bbq_graph_construct.py ran · violated contract no licence file found · pointer only · 4a53fb5a9f8c431e · report fixture: signature graph:dict/0/? · returned bool · level recorded 2026-09-24
decompose_action BBH_navigate/depth_increase.py ran no licence file found · pointer only · d336ec7d8d9af51b · report fixture: signature graph:dict/0/?, increase_ops:int/0/int, max_iterations:int/0/int · returned tuple · level recorded 2026-09-24
extract_input BBH_dyck/input_increase.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 9230c273439243c3 · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-24
extract_instructions BBH_navigate/depth_increase.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 581ef9fea4d7f89a · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-24
find_attrbutes_from_node_name BBQ/negative_attributes_generation.py ran no licence file found · pointer only · 04d79834f0effa32 · report fixture: signature graph:dict/0/?, person_node_name:str/0/str · returned list · level recorded 2026-09-24
generate_bracket_sequence_with_cutoff BBH_dyck/input_increase.py ran no licence file found · pointer only · 7e76059693a5a905 · report fixture: signature n:int/0/int, m:int/0/int · returned tuple · level recorded 2026-09-24
generate_valid_bracket_sequence BBH_dyck/input_increase.py ran · our draft was wrong fingerprinted no licence file found · pointer only · ac62197bc2186432 · report fixture: signature n:int/0/int · returned str · level recorded 2026-09-24
graph_to_instructions BBH_navigate/graph2text.py ran · our draft was wrong no licence file found · pointer only · 0211f85f91323fcb · report fixture: signature graph:dict/0/? · returned str · level recorded 2026-09-24
remove_label_information BBQ/graph2text.py ran · our draft was wrong no licence file found · pointer only · f452753a742fc950 · report fixture: signature graph:dict/0/? · returned dict · level recorded 2026-09-24
returns_to_start BBH_navigate/utils.py ran · our draft was wrong no licence file found · pointer only · 435e75b13316aade · report fixture: signature graph:dict/0/? · returned str · level recorded 2026-09-24
valid_decomposition BBH_navigate/depth_increase.py ran no licence file found · pointer only · 7782bbec569c6861 · report fixture: signature graph:dict/0/?, original_node:dict/0/?, decomposed_nodes:list/1/dict · returned bool · level recorded 2026-09-24

Tasks

Diversity

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