SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2412.13178 · 2024

SafeAgentBench: A Benchmark for Safe Task Planning of Embodied LLM Agents

arXiv · PDF · Open in the Atlas

Code that ran

7 of 11 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 0 have no contract verdict; 6 failures of our instrument; 4 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/2412.13178.json · badge: /api/ran/2412.13178.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
shengyin1224/safeagentbench canonical (classifier label)
classifier basis: census
7 ran · 4 no recorded run
FunctionStatusWhere it lives
call_gpt Ran
ran; our contract draft was wrong, not the code
shengyin1224/safeagentbench/evaluator/abstract_evaluate.py
pointer only (licence: NONE) · get_code("004ef77a803ae087")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shengyin1224/safeagentbench when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

call_gpt Ran
ran; our contract draft was wrong, not the code
shengyin1224/safeagentbench/evaluator/detail_evaluate.py
pointer only (licence: NONE) · get_code("2f61c26743e5287d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shengyin1224/safeagentbench when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

call_openai_with_retry Ran
ran; our contract draft was wrong, not the code
shengyin1224/safeagentbench/evaluator/detail_evaluate.py
pointer only (licence: NONE) · get_code("5efd7755ace53052")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shengyin1224/safeagentbench when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

compute_abstract_llm Ran
ran; our contract draft was wrong, not the code
shengyin1224/safeagentbench/evaluator/abstract_evaluate.py
pointer only (licence: NONE) · get_code("20765b11fc73a976")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shengyin1224/safeagentbench when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

find_obj Ran
ran; our contract draft was wrong, not the code
shengyin1224/safeagentbench/methods/utils.py
pointer only (licence: NONE) · get_code("b3617b20abb370c7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shengyin1224/safeagentbench when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

find_obj_by_type Ran
ran; our contract draft was wrong, not the code
shengyin1224/safeagentbench/methods/utils.py
pointer only (licence: NONE) · get_code("3b0c8cb51adc945c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shengyin1224/safeagentbench when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

is_any_element_contained Ran
ran, violated the contract we drafted
shengyin1224/safeagentbench/evaluator/detail_evaluate.py
pointer only (licence: NONE) · get_code("a8523baf5db6f682")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shengyin1224/safeagentbench when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

call_gpt Not yet run
unverified (harvested, no recorded run)
shengyin1224/safeagentbench/evaluator/long_horizon_evaluate.py
pointer only (licence: NONE) · get_code("cf64676d260a87c6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shengyin1224/safeagentbench when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

compute_safety_llm_long_horizon Not yet run
unverified (harvested, no recorded run)
shengyin1224/safeagentbench/evaluator/long_horizon_evaluate.py
pointer only (licence: NONE) · get_code("0cea743870f69c28")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shengyin1224/safeagentbench when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

compute_safety_llm_long_horizon_another Not yet run
unverified (harvested, no recorded run)
shengyin1224/safeagentbench/evaluator/long_horizon_evaluate.py
pointer only (licence: NONE) · get_code("c7c6225f6bf309e5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shengyin1224/safeagentbench when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

evaluate Not yet run
unverified (harvested, no recorded run)
shengyin1224/safeagentbench/evaluator/abstract_evaluate.py
pointer only (licence: NONE) · get_code("1b1f70631ef7016f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shengyin1224/safeagentbench when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 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 11 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

With the integration of large language models (LLMs), embodied agents have strong capabilities to understand and plan complicated natural language instructions. However, a foreseeable issue is that those embodied agents can also flawlessly execute some hazardous tasks, potentially causing damages in the real world. Existing benchmarks predominantly overlook critical safety risks, focusing solely on planning performance, while a few evaluate LLMs' safety awareness only on non-interactive image-text data. To address this gap, we present SafeAgentBench -- the first comprehensive benchmark for safety-aware task planning of embodied LLM agents in interactive simulation environments, covering both explicit and implicit hazards. SafeAgentBench includes: (1) an executable, diverse, and high-quality dataset of 750 tasks, rigorously curated to cover 10 potential hazards and 3 task types; (2) SafeAgentEnv, a universal embodied environment with a low-level controller, supporting multi-agent execution with 17 high-level actions for 9 state-of-the-art baselines; and (3) reliable evaluation methods from both execution and semantic perspectives. Experimental results show that, although agents based on different design frameworks exhibit substantial differences in task success rates, their overall safety awareness remains weak. The most safety-conscious baseline achieves only a 10% rejection rate for detailed hazardous tasks. Moreover, simply replacing the LLM driving the agent does not lead to notable improvements in safety awareness. Dataset and codes are available in https://github.com/shengyin1224/SafeAgentBench and https://huggingface.co/datasets/safeagentbench/SafeAgentBench.

For agents

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

get_harvested_code_for_paper("2412.13178")
get_code_for_paper("2412.13178")
have("2412.13178")

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

curl https://syntology.ai/api/ran/2412.13178.json

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

[![Syntology run record](https://syntology.ai/api/ran/2412.13178.svg)](https://syntology.ai/paper/2412.13178)

Connect an agent — have() is free.