Neural Bayesian Sequential Routing
Neural Bayesian Sequential Routing (NBSR) is a framework that models neural inference as active evidence accumulation over a hierarchical Directed Acyclic Graph (DAG). It uses a Dirichlet-Categorical conjugate framework with a global knowledge oracle to extract positive evidence vectors, and Gumbel-Softmax Straight-Through estimator for hard path-dependent routing. It provides mechanisms for uncertainty quantification, early exiting, OOD abstention, and cost-aware evidence acquisition. The paper proves monotonic precision increase and bounded variance, and demonstrates competitive performance across various tasks.
Article intelligence
Key points
- NBSR models inference as sequential evidence accumulation on a DAG
- Uses Dirichlet belief states and Gumbel-Softmax for routing
- Provides uncertainty quantification, early exit, and cost-aware mechanisms
- Theoretical guarantees on monotonic precision and experimental validation
Why it matters
This matters because NBSR models inference as sequential evidence accumulation on a DAG.
Technical impact
May affect model selection, inference cost, product capability, and evaluation benchmarks.
[2605.26147] Neural Bayesian Sequential Routing
[Submitted on 22 May 2026]
Title:Neural Bayesian Sequential Routing
View a PDF of the paper titled Neural Bayesian Sequential Routing, by Yongchao Huang
View PDF HTML (experimental)
Abstract:Human decision-making is sequential and uncertainty-aware, yet standard neural networks often rely on static, dense forward computation with limited visibility into evidence acquisition, uncertainty evolution, or when computation should stop. We introduce \textbf{Neural Bayesian Sequential Routing (NBSR)}, a framework that models neural inference as active evidence accumulation over a hierarchical Directed Acyclic Graph (DAG). Within a Dirichlet--Categorical conjugate framework, neural experts query a persistent global knowledge oracle to extract positive evidence vectors, which act as pseudo-counts and update a Dirichlet belief state by exact conjugate addition. Coupled with a Gumbel-Softmax Straight-Through estimator, this update enables hard, path-dependent routing while preserving surrogate gradients for end-to-end training. The resulting Dirichlet precision and entropy provide mechanisms for uncertainty quantification, entropy-based early exiting, OOD abstention, and cost-aware evidence acquisition. We prove that, under strictly positive evidence extraction, total Dirichlet precision increases monotonically along any valid trajectory and marginal predictive variance is bounded, formalizing sequential ``hypothesis sharpening''; under idealized capacity and optimization assumptions, the terminal Dirichlet expectation recovers the Bayes-optimal conditional distribution. Empirical evaluations across visual categorization, structured medical diagnosis, language modeling, partially observable control, and cost-aware Bayesian experimental design show that NBSR achieves competitive predictive performance while providing transparent routing traces, path-dependent evidence attribution, uncertainty-aware decision control, and resource-rational inference. Overall, NBSR offers a mathematically grounded framework for interpretable, modular, and resource-rational agentic AI.
Comments: 71 pages
Subjects:
Machine Learning (cs.LG)
Cite as: arXiv:2605.26147 [cs.LG]
(or arXiv:2605.26147v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2605.26147
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Yongchao Huang Dr. [view email] [v1] Fri, 22 May 2026 22:45:56 UTC (675 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Neural Bayesian Sequential Routing, by Yongchao Huang
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.LG
new | recent | 2026-05
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?)
IArxiv recommender toggle
IArxiv Recommender (What is IArxiv?)
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?)