Expertini Research Research

Browse Research Papers

29,638+ open-access research outputs.

โœ• Clear
๐Ÿ” bundit manaskasemsak
Showing 29638 results for "bundit manaskasemsak"
Computer Science Preprint PDF DOI

Claw-Eval-Live: A Live Agent Benchmark for Evolving Real-World Workflows

Chenxin Li, Zhengyang Tang, Huangxin Lin, Yunlong Lin, Shijue Huang, Shengyuan Liu, Bowen Ye, Rang Li, Lei Li, Benyou Wang, Yixuan Yuan ยท 2026

LLM agents are expected to complete end-to-end units of work across software tools, business services, and local workspaces. Yet many agent benchmarks freeze a curated task set at release time and graโ€ฆ

Read Paper โ†’
Neuroscience Preprint PDF DOI

On Agentic Behavioral Modeling

Dirk Ostwald, Rasmus Bruckner, Franziska Usee, Belinda Fleischmann, Joram Soch, Sean Mulready ยท 2026

Integrating theoretical neuroscience, decision theory, and probabilistic inference offers a promising route to understanding human cognition, yet concrete methodological bridges between agentic AI modโ€ฆ

Read Paper โ†’
Mathematics Preprint PDF DOI

Valuative independence for Calabi--Yau varieties

Harold Blum, Yuchen Liu ยท 2026

We construct valuatively independent bases for the space of sections of an ample line bundle on a log Calabi--Yau pair over a discretely valued field and the space of regular functions on an affine CYโ€ฆ

Read Paper โ†’
Physics Preprint PDF DOI

Regular ultracompact objects with anti-de Sitter cores as polymerized vacuum solutions

Hongguang Liu, Ioannis Soranidis ยท 2026

We present a systematic derivation of regular black hole solutions - and their horizonless counterparts - that achieve regularization via an anti-de Sitter core. These geometries emerge as polymerizedโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

Feature-Centric Methodology for Analyzing Cross-Chain NFT Migration Compatibility

Mohd Sameen Chishti, Damilare Peter Oyinloye, Jingyue Li ยท 2026

Cross-chain NFT migration refers to the process of transferring digital assets along with their associated functionalities and guarantees between distinct blockchain platforms. However, architectural โ€ฆ

Read Paper โ†’
Mathematics Preprint PDF DOI

On the Extremal Energy of Complex Unit Gain Dumbbell Graphs

Silin Huang ยท 2026

We study the extremal energy problem for complex unit gain graphs whose underlying graph is the dumbbell graph $D_{r,s,\ell}$. An explicit expression of its characteristic polynomial is derived in terโ€ฆ

Read Paper โ†’
AI & Data Science Preprint PDF DOI

Auditing Frontier Vision-Language Models for Trustworthy Medical VQA: Grounding Failures, Format Collapse, and Domain Adaptation

Xupeng Chen, Binbin Shi, Chenqian Le, Qifu Yin, Lang Lin, Haowei Ni, Ran Gong, Panfeng Li ยท 2026

Deploying vision-language models (VLMs) in clinical settings demands auditable behavior under realistic failure conditions, yet the failure landscape of frontier VLMs on specialized medical inputs is โ€ฆ

Read Paper โ†’
Mathematics Preprint PDF DOI

Towards Bigness equivalence

F. Laytimi, D. S. Nagaraj ยท 2026

On the flag variety $ \mathcal{F}l_s(E)$ associated to a vector bundle $E,$ , a sequence $s$ and a partition $a,$ there is a line bundle $\it Q^a_s$ on $ \mathcal{F}l_s(E).$ The aim of this papeโ€ฆ

Read Paper โ†’
AI & Data Science Preprint PDF DOI

Political Bias Audits of LLMs Capture Sycophancy to the Inferred Auditor

Petter Tornberg, Michelle Schimmel ยท 2026

Large language models (LLMs) are commonly evaluated for political bias based on their responses to fixed questionnaires, which typically place frontier models on the political left. A parallel literatโ€ฆ

Read Paper โ†’
Mathematics Preprint PDF DOI

$\mathbb{K}$-framings and $\mathbb{K}$-quadratic forms on surfaces

Nariya Kawazumi ยท 2026

We introduce the notions of $\mathbb{K}$-framings, based $\mathbb{K}$-framings and relative $\mathbb{K}$-framings of a compact connected oriented surface $\Sigma$ for any commutative ring $\mathbb{K}$โ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

Empire Amplifier: Uncovering and Contesting the Prioritization of Colonial Content on Platforms Through Community-Informed Algorithmic Auditing

Nel Escher, Bakyt Yrysov, Ashley McDermott, Daniel Chechelnitsky, Hermela Berehan Benyam, Nikola Banovic ยท 2026

Though online platforms claim to amplify Indigenous voices, Indigenous communities are worried that these systems are instead eroding their language and culture. We conduct a community-informed algoriโ€ฆ

Read Paper โ†’
Mathematics Preprint PDF DOI

Holomorphic Jet Modules and Holomorphic Connections for Noncommutative Complex Curves

Indranil Biswas, Satyajit Guin, Pradip Kumar ยท 2026

We extend Atiyah's holomorphic jet bundle formalism to holomorphic vector bundles over noncommutative algebras endowed with a bigraded differential calculus truncated at bidegree $(1,1)$; we refer to โ€ฆ

Read Paper โ†’
Physics Preprint PDF DOI

Nonadiabatic Renormalization Group for Strongly Coupled Multiscale Quantum Systems

Bing Gu ยท 2026

Complex quantum systems are often multiscale in nature with strong interactions between different scales. We present a novel idea: iteratively suppressing, rather than tracing out, the fast, high-enerโ€ฆ

Read Paper โ†’
AI & Data Science Preprint PDF DOI

Measurement Risk in Supervised Financial NLP: Rubric and Metric Sensitivity on JF-ICR

Sidi Chang, Peiying Zhu, Yuxiao Chen, Rongdong Chai ยท 2026

As LLMs become credible readers of earnings calls, investor-relations Q\&A, guidance, and disclosure language, supervised financial NLP benchmarks increasingly function as decision evidence for model โ€ฆ

Read Paper โ†’
AI & Data Science Preprint PDF DOI

TypeBandit: Type-Level Context Allocation and Reweighting for Effective Attribute Completion in Heterogeneous Graph Neural Networks

Ta-Yang Wang, Rajgopal Kannan, Viktor Prasanna ยท 2026

Heterogeneous graphs are widely used to model multi-relational systems, but missing node attributes remain a major bottleneck for downstream learning. In this paper, we identify and formalize type-depโ€ฆ

Read Paper โ†’
AI & Data Science Preprint PDF DOI

Learning When to Remember: Risk-Sensitive Contextual Bandits for Abstention-Aware Memory Retrieval in LLM-Based Coding Agents

Mehmet Iscan ยท 2026

Large language model (LLM)-based coding agents increasingly rely on external memory to reuse prior debugging experience, repair traces, and repository-local operational knowledge. However, retrieved mโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

Fisher Markets with Approximately Optimal Bundles and the Need for a PCP Theorem for PPAD

Argyrios Deligkas, John Fearnley, Alexandros Hollender, Themistoklis Melissourgos ยท 2026

We study the problem of computing a competitive equilibrium with approximately optimal bundles in Fisher markets with separable piecewise-linear concave (SPLC) utility functions, meaning that every buโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

Evaluating Epistemic Guardrails in AI Reading Assistants: A Behavioral Audit of a Minimal Prototype

Matthew Christian Agustin ยท 2026

Large language model (LLM) reading assistants are increasingly used in settings that require interpretation rather than simple retrieval. In these contexts, the central risk is not only error or unsafโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

Theory Under Construction: Orchestrating Language Models for Research Software Where the Specification Evolves

Halley Young, Nikolaj Bjorner ยท 2026

Large language models can now generate substantial code and draft research text, but research-software projects require more than either artifact alone. The mathematical thesis, executable system, benโ€ฆ

Read Paper โ†’
Mathematics Preprint PDF DOI

Hamilton decompositions of the directed 5-torus for odd modulus

SangHyun Park ยท 2026

We prove that the directed five-dimensional torus $D_5(m) = \operatorname{Cay}((\mathbb{Z}_m)^5, \{e_0, e_1, e_2, e_3, e_4\})$ has a Hamilton decomposition for every odd integer $m \geq 3$. This is thโ€ฆ

Read Paper โ†’
Page 1 of 1482 Next โ†’