SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.15538 · 2024

AgentLite: A Lightweight Library for Building and Advancing Task-Oriented LLM Agent System

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 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; 1 failure 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/2402.15538.json · badge: /api/ran/2402.15538.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
salesforceairesearch/agentlite canonical (classifier label)
classifier basis: census
2 ran · 0 no recorded run
FunctionStatusWhere it lives
name_checking Ran
ran, violated the contract we drafted
salesforceairesearch/agentlite/agentlite/agents/agent_utils.py
code served (permissive licence) · get_code("ab0e46e3357d450f")
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 torch
import numpy as np

torch.manual_seed(0)

# The function name_checking takes a single parameter 'name' which is a string.
# It checks if the string contains any whitespace characters (space, newline, tab).
# We need to provide a valid string argument.

ARGS = {
    "name": "valid_name_without_whitespace"
}
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 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
parse_action Ran
ran; our contract draft was wrong, not the code
salesforceairesearch/agentlite/agentlite/agents/agent_utils.py
code served (permissive licence) · get_code("8cbdbfe07b3e0678")
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 tuple, 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 re
import json

def parse_action(string: str) -> tuple[str, dict, bool]:
    """
    Parse an action string into an action type and an argument.
    """
    string = string.strip(' ').strip('.').strip(':').split('\n')[0]
    pattern = '^(\\w+)\\[(.+)\\]$'
    match = re.match(pattern, string)
    PARSE_FLAG = True
    if match:
        action_type = match.group(1).strip()
        arguments = match.group(2).strip()
        try:
            arguments = json.loads(arguments)
        except json.JSONDecodeError:
            PARSE_FLAG = False
            return (string, {}, PARSE_FLAG)
        return (action_type, arguments, PARSE_FLAG)
    else:
        PARSE_FLAG = False
        return (string, {}, PARSE_FLAG)


ARGS = {
    "string": 'action_name[{"key": "value", "number": 42}]'
}
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 tuple, ndim 1, dtype family float — a tuple 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

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 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 2 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

The booming success of LLMs initiates rapid development in LLM agents. Though the foundation of an LLM agent is the generative model, it is critical to devise the optimal reasoning strategies and agent architectures. Accordingly, LLM agent research advances from the simple chain-of-thought prompting to more complex ReAct and Reflection reasoning strategy; agent architecture also evolves from single agent generation to multi-agent conversation, as well as multi-LLM multi-agent group chat. However, with the existing intricate frameworks and libraries, creating and evaluating new reasoning strategies and agent architectures has become a complex challenge, which hinders research investigation into LLM agents. Thus, we open-source a new AI agent library, AgentLite, which simplifies this process by offering a lightweight, user-friendly platform for innovating LLM agent reasoning, architectures, and applications with ease. AgentLite is a task-oriented framework designed to enhance the ability of agents to break down tasks and facilitate the development of multi-agent systems. Furthermore, we introduce multiple practical applications developed with AgentLite to demonstrate its convenience and flexibility. Get started now at: \url{https://github.com/SalesforceAIResearch/AgentLite}.

For agents

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

get_harvested_code_for_paper("2402.15538")
get_code_for_paper("2402.15538")
have("2402.15538")

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

curl https://syntology.ai/api/ran/2402.15538.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.15538.svg)](https://syntology.ai/paper/2402.15538)

Connect an agent — have() is free.