SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2311.10751 · 2023

ProAgent: From Robotic Process Automation to Agentic Process Automation

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 4 failures of our instrument; 0 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2311.10751.json · badge: /api/ran/2311.10751.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
openbmb/proagent canonical (classifier label)
classifier basis: census
4 ran · 0 no recorded run
FunctionStatusWhere it lives
dump_common_things Ran
ran; our contract draft was wrong, not the code
openbmb/proagent/ProAgent/running_recorder.py
code served (permissive licence) · get_code("b39d16b5ad0fbe12")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn


class MockObjectWithToJson:
    """A mock object that has a to_json method."""
    def to_json(self):
        return {"json_key": "json_value"}


class MockNestedObject:
    """A mock object with to_json for testing nested structures."""
    def to_json(self):
        return "nested_json_output"


# Test with various types: primitives, dict, list, and objects with to_json
ARGS = {
    "object": {
        "primitive_str": "hello",
        "primitive_int": 42,
        "primitive_float": 3.14,
        "primitive_bool": True,
        "nested_dict": {
            "inner_key": "inner_value",
            "inner_int": 100
        },
        "list_of_primitives": [1, 2.5, "three", False],
        "list_with_object": [
            MockObjectWithToJson(),
            "string_item"
        ],
        "object_with_to_json": MockObjectWithToJson(),
        "nested_list": [[1, 2], ["a", "b"]],
        "mixed_nested": {
            "list_in_dict": [MockNestedObject(), 42],
            "dict_in_dict": {"deep": "value"}
        }
    }
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
highlight_code Ran
ran; our contract draft was wrong, not the code
openbmb/proagent/ProAgent/frontend/highlight_code.py
code served (permissive licence) · get_code("dda1f349e2fda46a")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

# Simple Python code string to highlight
code_to_highlight = """
def hello_world():
    print("Hello, World!")
    x = 42
    return x
"""

ARGS = {
    "code": code_to_highlight
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pygments, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
mainWorkflow Ran
ran; our contract draft was wrong, not the code
openbmb/proagent/ProAgent/handler/rpa_code_example.py
code served (permissive licence) · get_code("6c0120e6dd632909")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# The function takes trigger_input which is a list of dicts
# It simply assigns output_data = trigger_input and returns it
# So we need to construct a list of dictionaries

ARGS = {
    "trigger_input": [
        {
            "id": 1,
            "data": torch.randn(2, 4),
            "label": "sample_1"
        },
        {
            "id": 2,
            "data": torch.randn(2, 4),
            "label": "sample_2"
        }
    ]
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
remove_color_codes Ran
ran; our contract draft was wrong, not the code
openbmb/proagent/ProAgent/loggers/logs.py
code served (permissive licence) · get_code("f8f04c6b3e741b85")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import re

def remove_color_codes(s: str) -> str:
    """
    Removes color codes from a given string.
    
    Args:
        s (str): The string from which to remove color codes.
        
    Returns:
        str: The string with color codes removed.
    """
    ansi_escape = re.compile('\\x1B(?:[@-Z\\\\-_]|\\[[0-?]*[ -/]*[@-~])')
    return ansi_escape.sub('', s)


ARGS = {
    's': 'This is a string with \x1B[31mcolor codes\x1B[0m and \x1B[1;32mmore colors\x1B[0m here'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 3 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
remove_color_codes 4 other papers
1 dated earlier, 3 later
2309.02427 (2023-09)
Cognitive Architectures for Language Agents
2024.findings-emnlp.623 (2024 (year only))
Beyond Natural Language: LLMs Leveraging Alternative Formats for Enhanced Reasoning and Communication
2407.07061 (2024-07)
Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence
and 1 more not named here

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

From ancient water wheels to robotic process automation (RPA), automation technology has evolved throughout history to liberate human beings from arduous tasks. Yet, RPA struggles with tasks needing human-like intelligence, especially in elaborate design of workflow construction and dynamic decision-making in workflow execution. As Large Language Models (LLMs) have emerged human-like intelligence, this paper introduces Agentic Process Automation (APA), a groundbreaking automation paradigm using LLM-based agents for advanced automation by offloading the human labor to agents associated with construction and execution. We then instantiate ProAgent, an LLM-based agent designed to craft workflows from human instructions and make intricate decisions by coordinating specialized agents. Empirical experiments are conducted to detail its construction and execution procedure of workflow, showcasing the feasibility of APA, unveiling the possibility of a new paradigm of automation driven by agents. Our code is public at https://github.com/OpenBMB/ProAgent.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2311.10751")
get_code_for_paper("2311.10751")
have("2311.10751")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2311.10751.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2311.10751.svg)](https://syntology.ai/paper/2311.10751)

Connect an agent — have() is free.