SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.06147 · 2023

Reinforcement Learning in the Era of LLMs: What is Essential? What is needed? An RL Perspective on RLHF, Prompting, and Beyond

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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 0 have no contract verdict; 3 failures 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/2310.06147.json · badge: /api/ran/2310.06147.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
vanderschaarlab/prompt-oirl extension (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
extract_answer Ran
ran; our contract draft was wrong, not the code
vanderschaarlab/prompt-oirl/llama_exps/llama_step1_gen_offline.py
code served (permissive licence) · get_code("d95f990735eba145")
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) 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 re

ANS_RE = re.compile('#### (\\-?[0-9\\.\\,]+)')
INVALID_ANS = '[invalid]'

def extract_answer(completion):
    match = ANS_RE.search(completion)
    if match:
        match_str = match.group(1).strip()
        match_str = match_str.replace(',', '')
        return match_str
    else:
        return INVALID_ANS

# Test cases for the function
completion_with_answer = "Some text here\n#### 42.5\nMore text"
completion_with_negative = "Problem solution\n#### -123,456.78\nEnd"
completion_without_answer = "No answer here at all"
completion_with_comma = "Result is\n#### 1,000,000\nDone"

ARGS = {
    'completion': completion_with_answer
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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
get_examples_gsm8k Ran
ran; our contract draft was wrong, not the code
vanderschaarlab/prompt-oirl/llama_exps/llama_step1_gen_offline.py
code served (permissive licence) · get_code("a50e9db650b330ee")
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) and returned list, 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 os
import json
import tempfile
import shutil

# Create a temporary directory for test data
temp_dir = tempfile.mkdtemp()
data_dir = os.path.join(temp_dir, 'data')
os.makedirs(data_dir, exist_ok=True)

# Create a sample GSM8K JSONL file
train_data = [
    {"question": "What is 2 + 2?", "answer": "2 + 2 = 4"},
    {"question": "What is 5 * 3?", "answer": "5 * 3 = 15"},
]

train_path = os.path.join(data_dir, 'train.jsonl')
with open(train_path, 'w') as f:
    for item in train_data:
        f.write(json.dumps(item) + '\n')

# Create test split as well
test_data = [
    {"question": "What is 10 - 3?", "answer": "10 - 3 = 7"},
]

test_path = os.path.join(data_dir, 'test.jsonl')
with open(test_path, 'w') as f:
    for item in test_data:
        f.write(json.dumps(item) + '\n')

# Patch os.path.join to use our temp directory
original_join = os.path.join
def patched_join(*args):
    if args and args[0] == '../data/':
        return original_join(data_dir, *args[1:])
    return original_join(*args)

os.path.join = patched_join

ARGS = {
    'split': 'train'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 list, ndim 1, dtype family float — a list 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
read_jsonl Ran
ran; our contract draft was wrong, not the code
vanderschaarlab/prompt-oirl/llama_exps/llama_step1_gen_offline.py
code served (permissive licence) · get_code("951d55a786237f31")
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) and returned list, 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 json
import tempfile
import os

# Create a temporary JSONL file with valid JSON lines
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "test.jsonl")

with open(temp_file, 'w') as f:
    f.write(json.dumps({"key1": "value1", "key2": 42}) + "\n")
    f.write(json.dumps({"key1": "value2", "key2": 43}) + "\n")
    f.write(json.dumps({"key1": "value3", "key2": 44}) + "\n")

ARGS = {
    "path": temp_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 list, ndim 1, dtype family float — a list 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 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 2 the same month, 2 later) and 0 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
extract_answer 5 other papers
1 dated earlier, 1 the same month, 3 later
2309.06553 (2023-09)
Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RL
2310.07177 (2023-10)
Online Speculative Decoding
2401.10480 (2024-01)
Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step Reasoning
and 2 more not named here
read_jsonl 5 other papers
1 dated earlier, 1 the same month, 3 later
2309.06553 (2023-09)
Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RL
2310.07177 (2023-10)
Online Speculative Decoding
2312.12832 (2023-12)
Turning Dust into Gold: Distilling Complex Reasoning Capabilities from LLMs by Leveraging Negative Data
and 2 more not named here
get_examples_gsm8k 1 other paper
1 dated earlier
2309.06553 (2023-09)
Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RL

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 advancements in Large Language Models (LLMs) have garnered wide attention and led to successful products such as ChatGPT and GPT-4. Their proficiency in adhering to instructions and delivering harmless, helpful, and honest (3H) responses can largely be attributed to the technique of Reinforcement Learning from Human Feedback (RLHF). In this paper, we aim to link the research in conventional RL to RL techniques used in LLM research. Demystify this technique by discussing why, when, and how RL excels. Furthermore, we explore potential future avenues that could either benefit from or contribute to RLHF research. Highlighted Takeaways: 1. RLHF is Online Inverse RL with Offline Demonstration Data. 2. RLHF $>$ SFT because Imitation Learning (and Inverse RL) $>$ Behavior Cloning (BC) by alleviating the problem of compounding error. 3. The RM step in RLHF generates a proxy of the expensive human feedback, such an insight can be generalized to other LLM tasks such as prompting evaluation and optimization where feedback is also expensive. 4. The policy learning in RLHF is more challenging than conventional problems studied in IRL due to their high action dimensionality and feedback sparsity. 5. The main superiority of PPO over off-policy value-based methods is its stability gained from (almost) on-policy data and conservative policy updates.

For agents

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

get_harvested_code_for_paper("2310.06147")
get_code_for_paper("2310.06147")
have("2310.06147")

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

curl https://syntology.ai/api/ran/2310.06147.json

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

[![Syntology run record](https://syntology.ai/api/ran/2310.06147.svg)](https://syntology.ai/paper/2310.06147)

Connect an agent — have() is free.