research/notes/250109891-evolving-deeper-llm-thinking.md

---
title: '[2501.09891] Evolving Deeper LLM Thinking'
id: 250109891-evolving-deeper-llm-thinking
tags:
- deepread
created: '2026-06-10T00:24:58.674469Z'
source: https://arxiv.org/abs/2501.09891
source_domain: arxiv.org
fetched_at: '2026-06-10T00:24:58.674344Z'
fetch_provider: builtin
status: draft
type: note
tier: institutional
content_type: paper
deprecated: false
---

[2501.09891] Evolving Deeper LLM Thinking
Computer Science > Artificial Intelligence
arXiv:2501.09891
(cs)
[Submitted on 17 Jan 2025]
Title:
Evolving Deeper LLM Thinking
Authors:
Kuang-Huei Lee
,
Ian Fischer
,
Yueh-Hua Wu
,
Dave Marwood
,
Shumeet Baluja
,
Dale Schuurmans
,
Xinyun Chen
View a PDF of the paper titled Evolving Deeper LLM Thinking, by Kuang-Huei Lee and 6 other authors
View PDF
HTML (experimental)
Abstract:
We explore an evolutionary search strategy for scaling inference time compute in Large Language Models. The proposed approach, Mind Evolution, uses a language model to generate, recombine and refine candidate responses. The proposed approach avoids the need to formalize the underlying inference problem whenever a solution evaluator is available. Controlling for inference cost, we find that Mind Evolution significantly outperforms other inference strategies such as Best-of-N and Sequential Revision in natural language planning tasks. In the TravelPlanner and Natural Plan benchmarks, Mind Evolution solves more than 98% of the problem instances using Gemini 1.5 Pro without the use of a formal solver.
Subjects:
Artificial Intelligence (cs.AI)
Cite as:
arXiv:2501.09891
[cs.AI]
(or
arXiv:2501.09891v1
[cs.AI]
for this version)
https://doi.org/10.48550/arXiv.2501.09891
Focus to learn more
arXiv-issued DOI via DataCite
Submission history
From: Dale Schuurmans [
view email
]
[v1]
Fri, 17 Jan 2025 00:41:44 UTC (3,183 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Evolving Deeper LLM Thinking, by Kuang-Huei Lee and 6 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.AI
< prev
|
next >
new
|
recent
|
2025-01
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer
(
What is the Explorer?
)
Connected Papers Toggle
Connected Papers
(
What is Connected Papers?
)
Litmaps Toggle
Litmaps
(
What is Litmaps?
)
scite.ai Toggle
scite Smart Citations
(
What are Smart Citations?
)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv
(
What is alphaXiv?
)
Links to Code Toggle
CatalyzeX Code Finder for Papers
(
What is CatalyzeX?
)
DagsHub Toggle
DagsHub
(
What is DagsHub?
)
GotitPub Toggle
Gotit.pub
(
What is GotitPub?
)
Huggingface Toggle
Hugging Face
(
What is Huggingface?
)
Links to Code Toggle
Papers with Code
(
What is Papers with Code?
)
ScienceCast Toggle
ScienceCast
(
What is ScienceCast?
)
Demos
Demos
Replicate Toggle
Replicate
(
What is Replicate?
)
Spaces Toggle
Hugging Face Spaces
(
What is Spaces?
)
Spaces Toggle
TXYZ.AI
(
What is TXYZ.AI?
)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower
(
What are Influence Flowers?
)
Core recommender toggle
CORE Recommender
(
What is CORE?
)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community?
Learn more about arXivLabs
.
Which authors of this paper are endorsers?
|
Disable MathJax
(
What is MathJax?
)