Skip to content

Author

Bei-Ning Wu

We have 7 of 51 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Sep 2026

REBASE: Device-Cloud Experience Coherence for GUI Agents Across App Updates

A graphical user interface (GUI) agent that ships on a phone runs a small model and reuses experience: action paths recorded on earlier runs and cached from the cloud. When an app updates, part of this experience becomes silently wrong. On nine real app version pairs, an agent carrying experience recorded on the old ve...

Bei-Ning Wu, Jun Huang, Yan-Xiao Zhao · 3 citations
Open access Sep 2026

TRACE-FND: A Constrained Evidence-Agent Workflow with Trainable Graph Adjudication for Multimodal Fake-News Detection

Multimodal misinformation often preserves individually plausible text and images while manipulating their relation, provenance, timing, or omitted context. Existing detectors mainly learn fused correlations or verify normalized claims, leaving temporal validity, source reliability, evidence conflict, and material omiss...

Han Xue, Fu-You Mao, Xin Jiang et al. · 0 citations
#artificial intelligence Preprint Oct 2026

Not All Experience Belongs in the Weights: Component Routing for Self-Improving GUI Agents

This work introduces component routing, which splits the experience into locators, procedures, state facts and lessons and sends each component to the context or to the weights, compared on the same items across three backbone families, two environments and three seeds.

Bei-Ning Wu, Zi-Hao Ding, Jun Huang · 3 citations
#machine learning Preprint Sep 2026

Towards Understanding Momentum Acceleration in River-Valley Loss Landscape

Taken a step further, theoretical analysis is established that characterizes how momentum accelerates optimization by stabilizing large learning rates that can not be tolerated by vanilla GD without deviating significantly from the river.

Miao Lu, Ze-Yu Bian, Kai-Yue Wen et al. · 0 citations

INFUSER: Influence-Guided Self-Evolution Improves Reasoning

INFUSER is introduced, an iterative co-training framework with two co-evolving roles: a Generator that drafts questions and reference golden answers from a pool of unstructured, automatically collected documents, and a Solver that improves by training on them, and DuGRPO, a dual-normalized variant of GRPO, for generato...

Si-Yu Chen, Miao Lu, Bei-Ning Wu et al. · 0 citations
#artificial intelligence Preprint Sep 2026

ERRAND: Budgeted Maintenance of Agent Memory

This work introduces ERRAND, which treats revalidation as a priced errand, which clears every non-oracle policy on the preregistered calibers, primary in every setting and conditional at every binding budget, leading eager revalidation by 10.0pp at the base cap.

Bei-Ning Wu, Zi-Hao Ding, Jun Huang · 2 citations
Preprint Jul 2026

CrystalMem: Elastic Memory for Self-Evolving LLM Agents via Knowledge Crystallization

CrystalMem (Crystallized Memory), an elastic memory sidecar that demotes entries across four fidelity states under a crystallization-energy schedule, orders demotions by advantage-weighted influence with dependency coupling, and recovers capability through verified recrystallization under explicit compute and byte caps...

Bei-Ning Wu, Jun Huang · 3 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.