SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2505.04579 · IJCAI · 2025

Implicitly Aligning Humans and Autonomous Agents through Shared Task Abstractions

Katharina Von Der Wense, Alessandro Roncone, Stéphane Aroca-Ouellette, Miguel Aroca-Ouellette

arXiv · PDF · Open in the Atlas

Code that ran

2 of 7 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 2 have no contract verdict; 0 failures of our instrument; 5 no recorded run), measured 2026-11-22; 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/2505.04579.json · badge: /api/ran/2505.04579.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
HIRO-group/HA2 canonical (classifier label)
classifier basis not recorded on the link
2 ran · 5 no recorded run
FunctionStatusWhere it lives
facing Ran
ran on a synthesized input
HIRO-group/HA2/oai_agents/common/subtasks.py
code served (permissive licence) · get_code("d153b6200f2028a4")
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 numpy as np

class Player:
    def __init__(self, position, orientation):
        self.position = position
        self.orientation = orientation

# Create a simple 2D layout
layout = [
    ['g', 'g', 'w'],
    ['g', 'w', 'g'],
    ['w', 'g', 'g']
]

# Create a player at position (0, 0) facing right (1, 0)
player = Player(
    position=np.array([0, 0]),
    orientation=np.array([1, 0])
)

ARGS = {
    'layout': layout,
    'player': player
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — 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
get_output_shape Ran
ran on a synthesized input
HIRO-group/HA2/oai_agents/common/networks.py
code served (permissive licence) · get_code("99ea6ca6b4ffdecb")
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 Size. 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 as th
import torch.nn as nn

th.manual_seed(0)

# Build a minimal model that accepts input and produces output
class SimpleConvModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = nn.Conv2d(3, 16, kernel_size=3, padding=1)
        self.pool = nn.MaxPool2d(2, 2)
    
    def forward(self, x):
        x = self.conv1(x)
        x = self.pool(x)
        return x

model = SimpleConvModel()

# image_dim should be a tuple that can be unpacked with *
# Format: (batch_size, channels, height, width)
image_dim = (2, 3, 8, 8)

ARGS = {
    "model": model,
    "image_dim": image_dim,
}
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 Size — a Size output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Size output the recorded ndim 1 and dtype family int 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
calculate_completed_subtask Not yet run
unverified (harvested, no recorded run)
HIRO-group/HA2/oai_agents/common/subtasks.py
code served (permissive licence) · get_code("7f363f0bfb29bb68")
How it ran

no invocation recorded.

get_args_to_save Not yet run
unverified (harvested, no recorded run)
HIRO-group/HA2/oai_agents/common/arguments.py
code served (permissive licence) · get_code("f2a10fbe35283d71")
How it ran

no invocation recorded.

get_arguments Not yet run
unverified (harvested, no recorded run)
HIRO-group/HA2/oai_agents/common/arguments.py
code served (permissive licence) · get_code("5f6d9fe3bb842d1a")
How it ran

no invocation recorded.

is_held_obj Not yet run
unverified (harvested, no recorded run)
HIRO-group/HA2/oai_agents/agents/agent_utils.py
code served (permissive licence) · get_code("89af046dbb6e6088")
How it ran

no invocation recorded.

non_full_pot_exists Not yet run
unverified (harvested, no recorded run)
HIRO-group/HA2/oai_agents/common/subtasks.py
code served (permissive licence) · get_code("52245215641e4c82")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 1 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 6 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
get_output_shape 1 other paper
1 same year, order not determinable
2025.emnlp-main.1281 (2025 (year only))
ReSeeding Latent States for Sequential Language Understanding

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

In collaborative tasks, autonomous agents fall short of humans in their capability to quickly adapt to new and unfamiliar teammates. We posit that a limiting factor for zero-shot coordination is the lack of shared task abstractions, a mechanism humans rely on to implicitly align with teammates. To address this gap, we introduce HA 2 : Hierarchical Ad Hoc Agents, a framework leveraging hierarchical reinforcement learning to mimic the structured approach humans use in collaboration. We evaluate HA 2 in the Overcooked environment, demonstrating statistically significant improvement over baselines when paired with both unseen agents and humans, providing better resilience to environmental shifts, and outperforming state-of-the-art methods.

For agents

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

get_harvested_code_for_paper("2505.04579")
get_code_for_paper("2505.04579")
have("2505.04579")

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

curl https://syntology.ai/api/ran/2505.04579.json

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

[![Syntology run record](https://syntology.ai/api/ran/2505.04579.svg)](https://syntology.ai/paper/2505.04579)

Connect an agent — have() is free.