SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2308.01285 · 2023

Flows: Building Blocks of Reasoning and Collaborating AI

arXiv · PDF · Open in the Atlas

Code that ran

2 of 3 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; 2 failures of our instrument; 1 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/2308.01285.json · badge: /api/ran/2308.01285.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
epfl-dlab/aiflows canonical (classifier label)
classifier basis: census
2 ran · 0 no recorded run
epfl-dlab/cc_flows canonical (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
FunctionStatusWhere it lives
merge_delta_to_stream Ran
ran; our contract draft was wrong, not the code
epfl-dlab/aiflows/aiflows/backends/llm_lite.py
code served (permissive licence) · get_code("307902127a64cf9a")
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 numpy as np
from typing import Dict, Any

# Set random seed for reproducibility
torch.manual_seed(0)

# Construct valid arguments for merge_delta_to_stream
# The function merges a delta dict into a merged_stream dict
# It handles both nested dicts and scalar/string values that can be concatenated

merged_stream = {
    "choices": [
        {
            "delta": {
                "content": "Hello "
            }
        }
    ],
    "usage": {
        "prompt_tokens": 10,
        "completion_tokens": 5
    },
    "model": "gpt-3.5-turbo"
}

delta = {
    "choices": [
        {
            "delta": {
                "content": "world"
            }
        }
    ],
    "usage": {
        "prompt_tokens": 0,
        "completion_tokens": 1
    }
}

ARGS = {
    "merged_stream": merged_stream,
    "delta": delta
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, 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
merge_streams Ran
ran; our contract draft was wrong, not the code
epfl-dlab/aiflows/aiflows/backends/llm_lite.py
code served (permissive licence) · get_code("cd829c378ff4bedc")
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 numpy as np

torch.manual_seed(0)

# Construct a realistic streamed response from litellm
# This simulates multiple chunks being streamed back with partial content deltas
streamed_response = [
    {
        'choices': [
            {'index': 0, 'delta': {'content': 'Hello'}},
            {'index': 1, 'delta': {'content': 'Hi'}},
        ]
    },
    {
        'choices': [
            {'index': 0, 'delta': {'content': ' there'}},
            {'index': 1, 'delta': {'content': ' there'}},
        ]
    },
    {
        'choices': [
            {'index': 0, 'delta': {'content': '!'}},
        ]
    },
    {
        'choices': []  # Edge case: empty choices
    },
    {
        # Edge case: missing 'choices' key
    },
    {
        'choices': [
            {'index': 1, 'delta': {}},  # Edge case: no 'content' in delta
        ]
    },
]

n_chat_completion_choices = 2

ARGS = {
    'streamed_response': streamed_response,
    'n_chat_completion_choices': n_chat_completion_choices,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, 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
instantiate_flows Not yet run
unverified (harvested, no recorded run)
epfl-dlab/cc_flows/run_inference.py
code served (permissive licence) · get_code("93bda3868cc64742")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 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.

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

Recent advances in artificial intelligence (AI) have produced highly capable and controllable systems. This creates unprecedented opportunities for structured reasoning as well as collaboration among multiple AI systems and humans. To fully realize this potential, it is essential to develop a principled way of designing and studying such structured interactions. For this purpose, we introduce the conceptual framework Flows. Flows are self-contained building blocks of computation, with an isolated state, communicating through a standardized message-based interface. This modular design simplifies the process of creating Flows by allowing them to be recursively composed into arbitrarily nested interactions and is inherently concurrency-friendly. Crucially, any interaction can be implemented using this framework, including prior work on AI-AI and human-AI interactions, prompt engineering schemes, and tool augmentation. We demonstrate the potential of Flows on competitive coding, a challenging task on which even GPT-4 struggles. Our results suggest that structured reasoning and collaboration substantially improve generalization, with AI-only Flows adding +21 and human-AI Flows adding +54 absolute points in terms of solve rate. To support rapid and rigorous research, we introduce the aiFlows library embodying Flows. The aiFlows library is available at https://github.com/epfl-dlab/aiflows. Data and Flows for reproducing our experiments are available at https://github.com/epfl-dlab/cc_flows.

For agents

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

get_harvested_code_for_paper("2308.01285")
get_code_for_paper("2308.01285")
have("2308.01285")

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

curl https://syntology.ai/api/ran/2308.01285.json

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

[![Syntology run record](https://syntology.ai/api/ran/2308.01285.svg)](https://syntology.ai/paper/2308.01285)

Connect an agent — have() is free.