SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.15564 · ICML · 2026

Beyond Static Pipelines: Learning Dynamic Workflows for Text-to-SQL

Yihan Wang, Wei Xu, Peiyu Liu, Runyu Chen

arXiv · PDF · Open in the Atlas

Code that ran

11 of 16 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 10 failures of our instrument; 5 no recorded run), measured 2026-11-22; 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/2602.15564.json · badge: /api/ran/2602.15564.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
Satissss/SquRL canonical (classifier label)
classifier basis: census
11 ran · 5 no recorded run
FunctionStatusWhere it lives
compute_score_batch Ran
ran; our contract draft was wrong, not the code
Satissss/SquRL/verl/utils/reward_score/squrl.py
code served (permissive licence) · get_code("3e76ac8bdea12e77")
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 dict. 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 torch
import torch.nn as nn
from typing import Dict, List, Tuple

torch.manual_seed(0)

# Build the batch_responses dict
# The function expects: dict with instance_id keys, values are lists of (index, response_str, can_actors) tuples
batch_responses = {
    "instance_1": [
        (0, "```list\n['RSLSQLBiDirParser', 'MACSQLCoTParser']\n```", ['RSLSQLBiDirParser', 'MACSQLCoTParser']),
        (1, "```list\n['CHESSSelector']\n```", ['CHESSSelector']),
    ],
    "instance_2": [
        (2, "```list\n['MACSQLGenerator']\n```", ['MACSQLGenerator']),
    ],
}

ARGS = {
    "batch_responses": batch_responses,
    "api_port": 6517,
    "api_timeout": 1500,
    "batch_size": 2,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
convert_to_regular_types Ran
ran; our contract draft was wrong, not the code
Satissss/SquRL/verl/trainer/fsdp_sft_trainer.py
code served (permissive licence) · get_code("f887d72c9492d9ee")
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 dict. 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.

from omegaconf import ListConfig, DictConfig

# Test with various types that the function handles
nested_dict_config = DictConfig({
    "model": "bert",
    "layers": 12,
    "hidden_size": 768,
    "nested": DictConfig({"key": "value", "number": 42})
})

nested_list_config = ListConfig([1, 2, DictConfig({"a": "b"}), "test"])

regular_dict = {
    "name": "test",
    "values": [1, 2, 3],
    "nested": {"inner": "data"}
}

regular_list = [1, "string", {"key": "val"}, [1, 2, 3]]

mixed_tuple = (1, 2, {"nested": "dict"}, [4, 5])

simple_string = "hello"

simple_int = 42

simple_float = 3.14

ARGS = {
    "obj": nested_dict_config
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
omegaconf — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
create_huggingface_actor Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Satissss/SquRL/verl/utils/model.py
code served (permissive licence) · get_code("360c671d6041ba3b")
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 MockCausalLMModel. 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 torch
import torch.nn as nn
from unittest.mock import Mock, patch
from transformers import AutoConfig, PretrainedConfig

torch.manual_seed(0)

# Create a minimal mock config class
class MockPretrainedConfig(PretrainedConfig):
    model_type = "mock_model"
    
    def __init__(self, **kwargs):
        super().__init__(**kwargs)
        self.hidden_size = 64
        self.num_hidden_layers = 2
        self.num_attention_heads = 2
        self.intermediate_size = 128
        self.vocab_size = 1000
        self.max_position_embeddings = 512

# Create a minimal mock model
class MockCausalLMModel(nn.Module):
    def __init__(self, config):
        super().__init__()
        self.config = config
        self.embeddings = nn.Embedding(config.vocab_size, config.hidden_size)
        self.lm_head = nn.Linear(config.hidden_size, config.vocab_size)
    
    def forward(self, input_ids):
        x = self.embeddings(input_ids)
        return self.lm_head(x)

# Mock AutoConfig.from_pretrained to return our mock config
def mock_from_pretrained(model_name, trust_remote_code=False):
    return MockPretrainedConfig()

# Mock AutoModelForCausalLM.from_config to return our mock model
def mock_from_config(config, **kwargs):
    return MockCausalLMModel(config)

# Set up patches
import transformers
original_from_pretrained = transformers.AutoConfig.from_pretrained
original_from_config = transformers.AutoModelForCausalLM.from_config

transformers.AutoConfig.from_pretrained = staticmethod(mock_from_pretrained)
transformers.AutoModelForCausalLM.from_config = staticmethod(mock_from_config)

ARGS = {
    "model_name": "gpt2",
    "override_config_kwargs": {"hidden_size": 128, "num_hidden_layers": 4},
    "automodel_kwargs": {"trust_remote_code": False}
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, transformers — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type MockCausalLMModel — a MockCausalLMModel output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MockCausalLMModel 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
extract_step Ran
ran, honoured the contract we drafted
Satissss/SquRL/verl/trainer/fsdp_sft_trainer.py
code served (permissive licence) · get_code("216e28c040173a61")
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 int, ndim 0, dtype family int, 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 re

def extract_step(path):
    match = re.search('global_step_(\\d+)', path)
    if match:
        return int(match.group(1))
    return None

# Test case 1: path with global_step pattern
path_with_step = "/models/checkpoint_global_step_42/model.pt"

# Test case 2: path without global_step pattern
path_without_step = "/models/checkpoint_final/model.pt"

ARGS = {
    "path": path_with_step
}
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 int, ndim 0, dtype family int, 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
get_device_flops Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Satissss/SquRL/verl/utils/flops_counter.py
code served (permissive licence) · get_code("e13a5f688fa9602b")
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 float, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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

torch.manual_seed(0)

ARGS = {
    'unit': 'T'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, 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
get_kl_controller Ran
ran; our contract draft was wrong, not the code
Satissss/SquRL/verl/trainer/ppo/core_algos.py
code served (permissive licence) · get_code("45d08b3300b3da88")
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 AdaptiveKLController. 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 numpy as np

class Config:
    def __init__(self):
        self.critic = CriticConfig()
        self.kl_ctrl = KLCtrlConfig()

class CriticConfig:
    def __init__(self):
        self.kl_ctrl = KLCtrlConfig()

class KLCtrlConfig:
    def __init__(self, kl_type='fixed', kl_coef=0.01, target_kl=0.01, horizon=1000):
        self.type = kl_type
        self.kl_coef = kl_coef
        self.target_kl = target_kl
        self.horizon = horizon

config_fixed = Config()
config_fixed.critic.kl_ctrl.type = 'fixed'
config_fixed.critic.kl_ctrl.kl_coef = 0.01
config_fixed.kl_ctrl.horizon = 1000

config_adaptive = Config()
config_adaptive.critic.kl_ctrl.type = 'adaptive'
config_adaptive.critic.kl_ctrl.kl_coef = 0.01
config_adaptive.critic.kl_ctrl.target_kl = 0.01
config_adaptive.critic.kl_ctrl.horizon = 1000
config_adaptive.kl_ctrl.horizon = 1000

ARGS = {
    'config': config_adaptive
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type AdaptiveKLController — a AdaptiveKLController output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a AdaptiveKLController 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_local_temp_path Ran
ran; our contract draft was wrong, not the code
Satissss/SquRL/verl/utils/fs.py
code served (permissive licence) · get_code("34545dd1be06f719")
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.

import os
import tempfile

# Create a temporary directory for testing
temp_cache_dir = tempfile.mkdtemp()

ARGS = {
    "hdfs_path": "hdfs://example.com/data/file.txt",
    "cache_dir": temp_cache_dir
}
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
http_post_json Ran
ran; our contract draft was wrong, not the code
Satissss/SquRL/verl/utils/reward_score/squrl.py
code served (permissive licence) · get_code("e4cdc26940e02777")
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.

from urllib import request, error
import json
from unittest.mock import Mock, patch

# The function makes an HTTP POST request to a URL with a JSON payload.
# We need to provide:
# - url: a string (can be any valid URL format)
# - payload: a dict (will be JSON-encoded)
# - timeout: a float (optional, defaults to 720)

# Since this function makes actual network calls, we should provide valid-looking arguments
# that would work if a server were available. The function itself handles exceptions,
# so we just need to provide the basic inputs.

ARGS = {
    'url': 'http://localhost:8000/api/endpoint',
    'payload': {
        'key1': 'value1',
        'key2': 42,
        'key3': ['nested', 'list'],
        'key4': {'nested': 'dict'}
    },
    'timeout': 30.0
}
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
md5_encode Ran
ran; our contract draft was wrong, not the code
Satissss/SquRL/verl/utils/fs.py
code served (permissive licence) · get_code("6563b989ca963692")
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.

import hashlib

# The function md5_encode takes a path string and returns its MD5 hash hexdigest
# It only uses the path parameter as a string that gets encoded

ARGS = {
    "path": "/home/user/example/file.txt"
}
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
unpad_dataproto Ran
ran; our contract draft was wrong, not the code
Satissss/SquRL/verl/protocol.py
code served (permissive licence) · get_code("25f0ea3f460f6ce1")
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 DataProto. 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 torch
import numpy as np

torch.manual_seed(0)

class DataProto:
    """Stand-in class for DataProto that supports slicing."""
    def __init__(self, data):
        self.data = data
    
    def __getitem__(self, key):
        """Support slicing to return a new DataProto with sliced data."""
        sliced_data = self.data[key]
        return DataProto(sliced_data)
    
    def __repr__(self):
        return f"DataProto({self.data})"

# Create a small DataProto instance with some data
data_tensor = torch.randn(2, 4)
data_proto = DataProto(data_tensor)

ARGS = {
    "data": data_proto,
    "pad_size": 0
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DataProto — a DataProto output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataProto 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
validate_response_str Ran
ran; our contract draft was wrong, not the code
Satissss/SquRL/verl/utils/reward_score/squrl.py
code served (permissive licence) · get_code("eb5260f3cbdda280")
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. 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 torch
import numpy as np
from typing import List

# Set random seed for reproducibility
torch.manual_seed(0)

# Define test arguments for validate_response_str function
ARGS = {
    "response_str": """
    <answer>
    Here is the actor list:
    ```list
    ['RSLSQLBiDirParser', 'MACSQLCoTParser', 'CHESSGenerator']
    
    </answer>
    """,
    "can_actors": None
}
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 tuple — a tuple output has no array shape of its own; none is 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
compute_grpo_outcome_advantage Not yet run
unverified (harvested, no recorded run)
Satissss/SquRL/verl/trainer/ppo/core_algos.py
code served (permissive licence) · get_code("5e44de7d8d0e5d67")
How it ran

no invocation recorded.

copy_local_path_from_hdfs Not yet run
unverified (harvested, no recorded run)
Satissss/SquRL/verl/utils/fs.py
code served (permissive licence) · get_code("ac1030365ed166f2")
How it ran

no invocation recorded.

get_huggingface_actor_config Not yet run
unverified (harvested, no recorded run)
Satissss/SquRL/verl/utils/model.py
code served (permissive licence) · get_code("19472d4343d0a082")
How it ran

no invocation recorded.

initialize_global_process_group Not yet run
unverified (harvested, no recorded run)
Satissss/SquRL/verl/utils/distributed.py
code served (permissive licence) · get_code("f331ad3dce00d93b")
How it ran

no invocation recorded.

squeeze Not yet run
unverified (harvested, no recorded run)
Satissss/SquRL/verl/utils/model.py
code served (permissive licence) · get_code("3b15e2ac7497c441")
How it ran

no invocation recorded.

Also present in other papers' code

Of 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 7 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 7 the same month, 6 later) and 9 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
unpad_dataproto 89 other papers
36 dated earlier, 13 the same month, 37 later, 3 undated
2409.19256 (2024-09)
HybridFlow: A Flexible and Efficient RLHF Framework
2410.21236 (2024-10)
Flaming-hot Initiation with Regular Execution Sampling for Large Language Models
2025.findings-emnlp.1015 (2025 (year only))
MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learning
and 86 more not named here
squeeze 82 other papers
36 dated earlier, 12 the same month, 31 later, 3 undated
2409.19256 (2024-09)
HybridFlow: A Flexible and Efficient RLHF Framework
2410.21236 (2024-10)
Flaming-hot Initiation with Regular Execution Sampling for Large Language Models
2025.findings-emnlp.1015 (2025 (year only))
MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learning
and 79 more not named here
get_huggingface_actor_config 53 other papers
34 dated earlier, 5 the same month, 12 later, 2 undated
2409.19256 (2024-09)
HybridFlow: A Flexible and Efficient RLHF Framework
2410.21236 (2024-10)
Flaming-hot Initiation with Regular Execution Sampling for Large Language Models
2025.findings-emnlp.1015 (2025 (year only))
MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learning
and 50 more not named here
extract_step 19 other papers
13 dated earlier, 3 the same month, 2 later, 1 undated
2410.21236 (2024-10)
Flaming-hot Initiation with Regular Execution Sampling for Large Language Models
2025.findings-emnlp.1015 (2025 (year only))
MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learning
2502.14768 (2025-02)
Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning
and 16 more not named here
create_huggingface_actor 17 other papers
13 dated earlier, 1 the same month, 2 later, 1 undated
2025.findings-emnlp.1015 (2025 (year only))
MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learning
2502.14768 (2025-02)
Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning
2503.10460 (2025-03)
Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond
and 14 more not named here
convert_to_regular_types 7 other papers
5 dated earlier, 2 the same month
2410.21236 (2024-10)
Flaming-hot Initiation with Regular Execution Sampling for Large Language Models
2504.05520 (2025-04)
Efficient Reinforcement Finetuning via Adaptive Curriculum Learning
2505.04588 (2025-05)
ZeroSearch: Incentivize the Search Capability of LLMs without Searching
and 4 more not named here
get_kl_controller 3 other papers
1 the same month, 2 later
2602.04284 (2026-02)
Agent-Omit: Adaptive Context Omission for Efficient LLM Agents
2606.07705 (2026-06)
SAW: Stage-Aware Dynamic Weighting for Multi-Objective Reinforcement Learning in Large Language Models
2606.10646 (2026-06)
How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in 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

Text-to-SQL has recently achieved impressive progress, yet remains difficult to apply effectively in real-world scenarios. This gap stems from the reliance on single static workflows, fundamentally limiting scalability to out-of-distribution and long-tail scenarios. Instead of requiring users to select suitable methods through extensive experimentation, we attempt to enable systems to adaptively construct workflows at inference time. Through theoretical and empirical analysis, we demonstrate that optimal dynamic policies consistently outperform the best static workflow, with performance gains fundamentally driven by heterogeneity across candidate workflows. Motivated by this, we propose SquRL, a reinforcement learning framework that enhances LLMs' reasoning capability in adaptive workflow construction. We design a rule-based reward function and introduce two effective training mechanisms: dynamic actor masking to encourage broader exploration, and pseudo rewards to improve training efficiency. Experiments on widelyused Text-to-SQL benchmarks demonstrate that dynamic workflow construction consistently outperforms the best static workflow methods, with especially pronounced gains on complex and outof-distribution queries. The codes are available at https://github.com/Satissss/SquRL.

For agents

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

get_harvested_code_for_paper("2602.15564")
get_code_for_paper("2602.15564")
have("2602.15564")

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

curl https://syntology.ai/api/ran/2602.15564.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.15564.svg)](https://syntology.ai/paper/2602.15564)

Connect an agent — have() is free.