SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.07652 · EMNLP · 2024

StablePrompt: Automatic Prompt Tuning using Reinforcement Learning for Large Language Models

Jongsuk Kim, Junmo Kim, Minchan Kwon, Gaeun Kim, Haeil Lee

arXiv · PDF · Open in the Atlas

Code that ran

5 of 9 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 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/2410.07652.json · badge: /api/ran/2410.07652.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
kmc0207/Stableprompt canonical (classifier label)
classifier basis: census
5 ran · 4 no recorded run
FunctionStatusWhere it lives
choice_to_sentence Ran
ran; our contract draft was wrong, not the code
kmc0207/Stableprompt/dataset_utils.py
pointer only (licence: NONE) · get_code("6e0fa0aa42b63513")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kmc0207/Stableprompt 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.

f1_score Ran
ran, honoured the contract we drafted
kmc0207/Stableprompt/utils.py
pointer only (licence: NONE) · get_code("f019b3b51ce43942")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kmc0207/Stableprompt 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.

f1_score_single Ran
ran, honoured the contract we drafted
kmc0207/Stableprompt/utils.py
pointer only (licence: NONE) · get_code("a424dfef1368b0fb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kmc0207/Stableprompt 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.

normalize_answer Ran
ran; our contract draft was wrong, not the code
kmc0207/Stableprompt/utils.py
pointer only (licence: NONE) · get_code("d8af265929dc927f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kmc0207/Stableprompt 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.

normalize_prediction Ran
ran; our contract draft was wrong, not the code
kmc0207/Stableprompt/ii_utils.py
pointer only (licence: NONE) · get_code("d743b4d4da5336f3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kmc0207/Stableprompt 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.

load_annotation Not yet run
unverified (harvested, no recorded run)
kmc0207/Stableprompt/ii_utils.py
pointer only (licence: NONE) · get_code("0a15b06668074e60")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kmc0207/Stableprompt 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.

load_bigbench Not yet run
unverified (harvested, no recorded run)
kmc0207/Stableprompt/dataset_utils.py
pointer only (licence: NONE) · get_code("12eff4765374d162")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kmc0207/Stableprompt 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.

load_data Not yet run
unverified (harvested, no recorded run)
kmc0207/Stableprompt/ii_utils.py
pointer only (licence: NONE) · get_code("5e6da3a9f82347b0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kmc0207/Stableprompt 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.

load_mmlu Not yet run
unverified (harvested, no recorded run)
kmc0207/Stableprompt/dataset_utils.py
pointer only (licence: NONE) · get_code("4308233613a9bd58")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kmc0207/Stableprompt 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 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 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, 1 later) and 8 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
normalize_prediction 2 other papers
1 dated earlier, 1 later
2205.10782 (2022-05)
Instruction Induction: From Few Examples to Natural Language Task Descriptions
2510.25808 (2025-10)
PRESTO: Preimage-Informed Instruction Optimization for Prompting Black-Box LLMs

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

Finding appropriate prompts for the specific task has become an important issue as the usage of Large Language Models (LLM) has expanded. Reinforcement Learning (RL) is widely used for prompt tuning, but its inherent instability and environmental dependency make it difficult to use in practice. In this paper, we propose StablePrompt, which strikes a balance between training stability and search space, mitigating the instability of RL and producing high-performance prompts. We formulate prompt tuning as an online RL problem between the agent and target LLM and introduce Adaptive Proximal Policy Optimization (APPO). APPO introduces an LLM anchor model to adaptively adjust the rate of policy updates. This allows for flexible prompt search while preserving the linguistic ability of the pre-trained LLM. StablePrompt outperforms previous methods on various tasks including text classification, question answering, and text generation. Our code can be found in github.

For agents

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

get_harvested_code_for_paper("2410.07652")
get_code_for_paper("2410.07652")
have("2410.07652")

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

curl https://syntology.ai/api/ran/2410.07652.json

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

[![Syntology run record](https://syntology.ai/api/ran/2410.07652.svg)](https://syntology.ai/paper/2410.07652)

Connect an agent — have() is free.