SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2404.12253 · NeurIPS · 2024

Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing

Lei Han, Dong Yu, Dian Yu, Baolin Peng, Ye Tian, Linfeng Song, Jin Lifeng, Haitao Mi

arXiv · PDF · Open in the Atlas

Code that ran

14 of 18 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 1 violated it and 1 has no contract verdict; 11 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/2404.12253.json · badge: /api/ran/2404.12253.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
YeTianJHU/AlphaLLM canonical (classifier label)
classifier basis: census
11 ran · 2 no recorded run
yetianjhu/alphallm community
Papers with Code archive
3 ran · 2 no recorded run
FunctionStatusWhere it lives
MonteCarloTreeSearchNode Ran
ran on a synthesized input · constructed an object; no result was computed
yetianjhu/alphallm/search/mcts.py
pointer only (licence: NONE) · get_code("ef6c4dacecbd6cb6")
How it ran

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

convert_to_left_equation Ran
ran; our contract draft was wrong, not the code
YeTianJHU/AlphaLLM/utils/gsm8k_dataset.py
pointer only (licence: NONE) · get_code("f75cff37d1f59a84")
How it ran

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

gen_experiment_name Ran
ran; our contract draft was wrong, not the code
YeTianJHU/AlphaLLM/search/experiment.py
pointer only (licence: NONE) · get_code("b4a213ba708b085d")
How it ran

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

identify_and_format_decimal Ran
ran; our contract draft was wrong, not the code
YeTianJHU/AlphaLLM/server/extract_client_example.py
pointer only (licence: NONE) · get_code("72bf3605afc839b3")
How it ran

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

linear_activation Ran
ran, honoured the contract we drafted
YeTianJHU/AlphaLLM/models/rmgpt_model.py
pointer only (licence: NONE) · get_code("29136163302afc0c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, YeTianJHU/AlphaLLM 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_data Ran
ran; our contract draft was wrong, not the code
YeTianJHU/AlphaLLM/utils/gsm8k_dataset.py
pointer only (licence: NONE) · get_code("2c7670bbc9fce517")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, YeTianJHU/AlphaLLM 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_data_gsm8k Ran
ran; our contract draft was wrong, not the code
YeTianJHU/AlphaLLM/search/experiment.py
pointer only (licence: NONE) · get_code("2fc084634834c538")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, YeTianJHU/AlphaLLM 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_step_data Ran
ran; our contract draft was wrong, not the code
YeTianJHU/AlphaLLM/utils/gsm8k_dataset.py
pointer only (licence: NONE) · get_code("f1ff5a1574cecc9d")
How it ran

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

remove_enclosed_strings Ran
ran; our contract draft was wrong, not the code
YeTianJHU/AlphaLLM/server/extract_client_example.py
pointer only (licence: NONE) · get_code("bbbbf23c8b624b94")
How it ran

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

replace_enclosed_strings Ran
ran; our contract draft was wrong, not the code
YeTianJHU/AlphaLLM/server/extract_client_example.py
pointer only (licence: NONE) · get_code("48305b97411c62ac")
How it ran

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

select_url Ran
ran; our contract draft was wrong, not the code
yetianjhu/alphallm/search/mcts.py
pointer only (licence: NONE) · get_code("3b7ff9f187ac8a13")
How it ran

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

str2bool Ran
ran, violated the contract we drafted
YeTianJHU/AlphaLLM/search/experiment.py
pointer only (licence: NONE) · get_code("7c508037b40522af")
How it ran

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

to_device Ran
ran; our contract draft was wrong, not the code
YeTianJHU/AlphaLLM/utils/utils.py
pointer only (licence: NONE) · get_code("387b9e6c4f21dd62")
How it ran

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

weighted_vote Ran
ran; our contract draft was wrong, not the code
yetianjhu/alphallm/search/mcts.py
pointer only (licence: NONE) · get_code("73b222be68d63972")
How it ran

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

MCTS Not yet run
unverified (harvested, no recorded run)
yetianjhu/alphallm/search/mcts.py
pointer only (licence: NONE) · get_code("d3ceda385feb848e")
How it ran

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

format_llama2 Not yet run
unverified (harvested, no recorded run)
yetianjhu/alphallm/search/mcts.py
pointer only (licence: NONE) · get_code("fe0186765fc4b2a7")
How it ran

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

get_tokenizer Not yet run
unverified (harvested, no recorded run)
YeTianJHU/AlphaLLM/utils/utils.py
pointer only (licence: NONE) · get_code("f4d93f19b3b4e1ac")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, YeTianJHU/AlphaLLM 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_hf_tokenizer Not yet run
unverified (harvested, no recorded run)
YeTianJHU/AlphaLLM/utils/utils.py
pointer only (licence: NONE) · get_code("e90b184086a6543b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, YeTianJHU/AlphaLLM 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 18 samples lifted from this paper's linked repositories, 18 carry a function identity and 0 do not. Of the 18 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 1 the same month, 2 later) and 14 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
str2bool 175 other papers
118 dated earlier, 1 the same month, 55 later, 1 same year, order not determinable · 2 only as an assembly brick
1406.6247 (2014-06)
Recurrent Models of Visual Attention
1603.09382 (2016-03)
Deep Networks with Stochastic Depth
1710.10196 (2017-10)
Progressive Growing of GANs for Improved Quality, Stability, and Variation
and 172 more not named here
to_device 6 other papers
3 dated earlier, 2 later, 1 same year, order not determinable
2310.20246 (2023-10)
Breaking Language Barriers in Multilingual Mathematical Reasoning: Insights and Observations
2024.naacl-long.326 (2024 (year only))
LSTDial: Enhancing Dialogue Generation via Long-and Short-Term Measurement Feedback
2402.05808 (2024-02)
Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning
and 3 more not named here
get_tokenizer 2 other papers
1 dated earlier, 1 same year, order not determinable
2310.20246 (2023-10)
Breaking Language Barriers in Multilingual Mathematical Reasoning: Insights and Observations
2024.naacl-long.326 (2024 (year only))
LSTDial: Enhancing Dialogue Generation via Long-and Short-Term Measurement Feedback
load_hf_tokenizer 1 other paper
1 dated earlier
2310.10505 (2023-10)
ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models

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

Despite the impressive capabilities of Large Language Models (LLMs) on various tasks, they still struggle with scenarios that involves complex reasoning and planning. Self-correction and self-learning emerge as viable solutions, employing strategies that allow LLMs to refine their outputs and learn from self-assessed rewards. Yet, the efficacy of LLMs in self-refining its response, particularly in complex reasoning and planning task, remains dubious. In this paper, we introduce ALPHALLM for the self-improvements of LLMs, which integrates Monte Carlo Tree Search (MCTS) with LLMs to establish a self-improving loop, thereby enhancing the capabilities of LLMs without additional annotations. Drawing inspiration from the success of AlphaGo, ALPHALLM addresses the unique challenges of combining MCTS with LLM for self-improvement, including data scarcity, the vastness search spaces of language tasks, and the subjective nature of feedback in language tasks. ALPHALLM is comprised of prompt synthesis component, an efficient MCTS approach tailored for language tasks, and a trio of critic models for precise feedback. Our experimental results in mathematical reasoning tasks demonstrate that ALPHALLM significantly enhances the performance of LLMs without additional annotations, showing the potential for self-improvement in LLMs. The code is available at https://github.com/YeTianJHU/AlphaLLM.

For agents

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

get_harvested_code_for_paper("2404.12253")
get_code_for_paper("2404.12253")
have("2404.12253")

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

curl https://syntology.ai/api/ran/2404.12253.json

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

[![Syntology run record](https://syntology.ai/api/ran/2404.12253.svg)](https://syntology.ai/paper/2404.12253)

Connect an agent — have() is free.