SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2210.12485 · EMNLP · 2022

DANLI: Deliberative Agent for Following Natural Language Instructions

Yichi Zhang, Ziqiao Ma, Jianing Yang, Jiayi Pan, Shane Storks, Nikhil Devraj, Keunwoo Peter, Yu Yuwei, Bao Chai

arXiv · PDF · Open in the Atlas

Code that ran

3 of 6 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, 1 violated it and 2 have no contract verdict; 0 failures of our instrument; 3 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/2210.12485.json · badge: /api/ran/2210.12485.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
sled-group/DANLI canonical (classifier label)
classifier basis not recorded on the link
3 ran · 3 no recorded run
FunctionStatusWhere it lives
ithor_oid_to_object_class Ran
ran on a synthesized input
sled-group/DANLI/ithor_assets/object_definitions.py
code served (permissive licence) · get_code("eb415cd40f9c474e")
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.

# Setup code for ithor_oid_to_object_class

# Analyze the function:
# - Takes one parameter: objectId_str (a string)
# - Splits by '|' delimiter
# - Returns either first element (if 4 parts) or last element split by '_' (first part)
# - Examples show various iTHOR object ID formats

ARGS = {
    "objectId_str": "Book|1|2|3"
}
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
object_intid_to_string Ran
ran on a synthesized input
sled-group/DANLI/ithor_assets/object_definitions.py
code served (permissive licence) · get_code("9c0c9c4786089460")
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.

# Set up the global state for the function
_INTERACTABLE_OBJECTS = ['door', 'chair', 'table']
_STRUCTURAL_OBJECTS = ['wall', 'floor', 'ceiling']

UNK_OBJ_STR = 'OTHERS'

OBJECT_CLASSES = sorted(list(set(_INTERACTABLE_OBJECTS + _STRUCTURAL_OBJECTS)))

OBJECT_INT_TO_STR = {i: o for i, o in enumerate(OBJECT_CLASSES)}

def object_intid_to_string(intid: int) -> str:
    global OBJECT_INT_TO_STR, UNK_OBJ_STR
    return OBJECT_INT_TO_STR.get(intid, UNK_OBJ_STR)

# Define arguments for the function
ARGS = {
    'intid': 2
}
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
process_alive Ran
ran, violated the contract we drafted
sled-group/DANLI/start_x.py
code served (permissive licence) · get_code("f20433e6b6a47e71")
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 bool, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 os
import subprocess

# Get the current process ID to use as a valid, alive process
current_pid = os.getpid()

ARGS = {
    "pid": current_pid
}
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 bool, ndim 0, dtype family float, shape () — shape () as a later run recorded it
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
find_devices Not yet run
unverified (harvested, no recorded run)
sled-group/DANLI/start_x.py
code served (permissive licence) · get_code("527a96e1b70deb8a")
How it ran

no invocation recorded.

generate_xorg_conf Not yet run
unverified (harvested, no recorded run)
sled-group/DANLI/start_x.py
code served (permissive licence) · get_code("aa6655b550db6453")
How it ran

no invocation recorded.

object_str_to_intid Not yet run
unverified (harvested, no recorded run)
sled-group/DANLI/ithor_assets/object_definitions.py
code served (permissive licence) · get_code("a62edde9a2236b2f")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 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, 0 later) and 5 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
process_alive 1 other paper
1 dated earlier
1712.05474 (2017-12)
AI2-THOR: An Interactive 3D Environment for Visual AI

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 years have seen an increasing amount of work on embodied AI agents that can perform tasks by following human language instructions. However, most of these agents are reactive, meaning that they simply learn and imitate behaviors encountered in the training data. These reactive agents are insufficient for longhorizon complex tasks. To address this limitation, we propose a neuro-symbolic deliberative agent that, while following language instructions, proactively applies reasoning and planning based on its neural and symbolic representations acquired from past experience (e.g., natural language and egocentric vision). We show that our deliberative agent achieves greater than 70% improvement over reactive baselines on the challenging TEACh benchmark. Moreover, the underlying reasoning and planning processes, together with our modular framework, offer impressive transparency and explainability to the behaviors of the agent. This enables an in-depth understanding of the agent's capabilities, which shed light on challenges and opportunities for future embodied agents for instruction following. The code is available at https://github.com/sled-group/DANLI.

For agents

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

get_harvested_code_for_paper("2210.12485")
get_code_for_paper("2210.12485")
have("2210.12485")

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

curl https://syntology.ai/api/ran/2210.12485.json

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

[![Syntology run record](https://syntology.ai/api/ran/2210.12485.svg)](https://syntology.ai/paper/2210.12485)

Connect an agent — have() is free.