Papers › Causal Agent based on Large Language Model

Causal Agent based on Large Language Model

13 Aug 2024arXiv:2408.06849archive 2025-07-28

Kairong Han, Kun Kuang, Ziyu Zhao, Junjian Ye, Fei Wu

Large language models (LLMs) have achieved significant success across various domains. However, the inherent complexity of causal problems and causal theory poses challenges in accurately describing them in natural language, making it difficult for LLMs to comprehend and use them effectively. Causal methods are not easily conveyed through natural language, which hinders LLMs' ability to apply them accurately. Additionally, causal datasets are typically tabular, while LLMs excel in handling natural language data, creating a structural mismatch that impedes effective reasoning with tabular data. This lack of causal reasoning capability limits the development of LLMs. To address these challenges, we have equipped the LLM with causal tools within an agent framework, named the Causal Agent, enabling it to tackle causal problems. The causal agent comprises tools, memory, and reasoning modules. In the tools module, the causal agent applies causal methods to align tabular data with natural language. In the reasoning module, the causal agent employs the ReAct framework to perform reasoning through multiple iterations with the tools. In the memory module, the causal agent maintains a dictionary instance where the keys are unique names and the values are causal graphs. To verify the causal ability of the causal agent, we established a benchmark consisting of four levels of causal problems: variable level, edge level, causal graph level, and causal effect level. We generated a test dataset of 1.3K using ChatGPT-3.5 for these four levels of issues and tested the causal agent on the datasets. Our methodology demonstrates remarkable efficacy on the four-level causal problems, with accuracy rates all above 80%. For further insights and implementation details, our code is accessible via the GitHub repository https://github.com/Kairong-Han/Causal_Agent.

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 1 repository linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 14 samples from 1 repository, 11 ran (7 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

kairong-han/causal_agent officialmentioned in paperpytorchMITSyntology: 14 samples, 11 ran (4 instrument-failed) · 3 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: 11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 3 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
2ran · our draft was wrong
2ran; the contract check could not run
6ran
3unverified

Licence: 0 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 kairong-han/causal_agent. “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.

kairong-han/causal_agent official repository 14 samples, 11 ran (4 instrument-failed) · 3 unverified
Stein_hess SCORE-main/stein.py ran MIT (permissive) · a8a7a259db8a81b3 · report fixture: signature X:Tensor/2/float, eta_G:float/0/float, eta_H:float/0/float, s:NoneType/0/? · returned Tensor · level recorded 2026-09-24
add_noise in 46 papers
census: 9 implementations from 9 papers, 8 distinct outputs across 3 buckets, one shared input per bucket
main_QR.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · bb340e38e6e61436 · report fixture: signature data:ndarray/2/float, noise_level:float/0/float · returned ndarray · level recorded 2026-09-24
compute_top_order SCORE-main/stein.py ran MIT (permissive) · 00230c910f8f28f5 · report fixture: signature X:Tensor/2/float, eta_G:float/0/float, eta_H:float/0/float, normalize_var:bool/0/bool, dispersion:str/0/str · returned list · level recorded 2026-09-24
edge_dir util.py ran MIT (permissive) · 9a227dfd5452fed4 · report fixture: signature X:int/0/int, Y:int/0/int, adj1:list/1/list · returned Edge · level recorded 2026-09-24
edge_num SCORE-main/demo_SCORE.py ran · honoured contract fingerprinted MIT (permissive) · 63790fd8bd85e92f · report fixture: signature node_num:int/0/int · returned list · level recorded 2026-09-24
find_all_paths util.py ran MIT (permissive) · 541d7f28dbdb0e00 · report fixture: signature i:int/0/int, j:int/0/int, adj:dict/0/?, path:list/1/empty · returned list · level recorded 2026-09-24
full_DAG SCORE-main/utils.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed MIT (permissive) · a86ab79ff7c3ca42 · report fixture: signature top_order:list/1/int · returned ndarray · level recorded 2026-09-22
get_name in 20 papers dataset_gt.py ran MIT (permissive) · 5f47c429ede66b1c · report fixture: signature to_find:list/1/str, name_list:list/1/str · returned list · level recorded 2026-09-24
np_to_csv SCORE-main/utils.py ran · our draft was wrong MIT (permissive) · 7f33c8711d7b2d37 · report fixture: signature array:ndarray/2/int, save_path:str/0/str · returned str · level recorded 2026-09-24
simulate_dag SCORE-main/utils.py ran MIT (permissive) · 003d81116b4a4fb5 · report fixture: signature d:int/0/int, s0:int/0/int, graph_type:str/0/str, triu:bool/0/bool · returned ndarray · level recorded 2026-09-24
triangle_to_adj util.py ran · our draft was wrong MIT (permissive) · b036a30566ea1159 · report fixture: signature triangle:list/1/list · returned dict · level recorded 2026-09-24
Stein_pruning SCORE-main/stein.py unverified MIT (permissive) · 5da3b16530d01830 · report
get_code_result baseline-codellm.py unverified MIT (permissive) · 55e01338dc26c5f7 · report

Tasks

Language ModelingLanguage ModellingLarge Language Modelmodel

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ALIGN

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