Search for Truth from Reasoning: A Dynamic Representation Editing Framework for Steering LLM Trajectories
Current methods to enhance LLM reasoning, such as Chain-of-Thought and "Wait" prompts, mainly encourage models to think more but often fail to guide them toward truth. This paper investigates the geometry of truth within reasoning chains and proposes DynaSteer, a dynamic representation editing framework. It uses pattern clustering and Fisher-LDA to purify truth and dynamically monitors lookahead entropy to selectively steer and roll back trajectories, achieving strong results on MATH benchmarks and out-of-domain coding tasks.
[2606.28589] Search for Truth from Reasoning: A Dynamic Representation Editing Framework for Steering LLM Trajectories
[Submitted on 26 Jun 2026]
Title:Search for Truth from Reasoning: A Dynamic Representation Editing Framework for Steering LLM Trajectories
View a PDF of the paper titled Search for Truth from Reasoning: A Dynamic Representation Editing Framework for Steering LLM Trajectories, by Tianlong Wang and 7 other authors
View PDF HTML (experimental)
Abstract:Current approaches to enhance Large Language Model (LLM) reasoning, such as Chain-of-Thought and "Wait" prompts, primarily encourage models to think more, yet often fail to guide them toward Truth. While Representation Editing (RepE) offers a intrinsic control, its application to dynamic reasoning trajectories remains underexplored. In this work, we bridge this gap by investigating the geometry of truth within unfolding reasoning chains. We uncover three critical insights: (1) Truth is encoded at the sentence level and is entangled with latent reasoning patterns; (2) Effective intervention follows an Uncertainty Principle and a Decay Effect, requiring localization to early, high-entropy forks; (3) Naive steering vectors suffer from noise, risking collateral damage to correct trajectories. Based on these findings, we propose DynaSteer, a dynamic RepE framework. DynaSteer employs pattern clustering to disentangle reasoning manifolds and utilizes Fisher-LDA to project purified truth. By dynamically monitoring lookahead entropy, it selectively steers and rolls back trajectories only when necessary. Comprehensive experimental results on several MATH benchmark verify the effectiveness of DynaSteer, and experiments on out-of-domain coding tasks further confirm its generalization ability. Our code is publicly available at this https URL.
Comments: Accepted by ICML'26
Subjects:
Artificial Intelligence (cs.AI)
Cite as: arXiv:2606.28589 [cs.AI]
(or arXiv:2606.28589v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2606.28589
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Weibin Liao [view email] [v1] Fri, 26 Jun 2026 20:33:55 UTC (3,082 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Search for Truth from Reasoning: A Dynamic Representation Editing Framework for Steering LLM Trajectories, by Tianlong Wang and 7 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.AI
new | recent | 2026-06
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
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?)
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?)