Expertini Research Research

Browse Research Papers

823+ open-access research outputs.

✕ Clear
🔍 devon hjelm
Showing 823 results for "devon hjelm"
Computer Science Preprint PDF DOI

Agentic AI in the Software Development Lifecycle: Architecture, Empirical Evidence, and the Reshaping of Software Engineering

Happy Bhati · 2026

The arrival of large language models (LLMs) capable of multi-step reasoning, tool use, and long-horizon planning has produced a qualitative shift in software engineering. Where earlier code-completion…

Read Paper →
AI & Data Science Preprint PDF DOI

HELM: Harness-Enhanced Long-horizon Memory for Vision-Language-Action Manipulation

Zijian Zeng, Fei Ding, Huiming Yang, Xianwei Li · 2026

Vision-Language-Action (VLA) models fail systematically on long-horizon manipulation tasks despite strong short-horizon performance. We show that this failure is not resolved by extending context leng…

Read Paper →
Computer Science Preprint PDF DOI

Reliability of AI Bots Footprints in GitHub Actions CI/CD Workflows

Syed Muhammad Ashhar Shah, Sehrish Habib, Muizz Hussain, Maryam Abdul Ghafoor, Abdul Ali Bangash · 2026

Continuous Integration and Deployment (CI/CD) workflows are central to modern software delivery, yet the reliability of agentic AI bots operating within these workflows remain underexplored. Using pul…

Read Paper →
Economics & Finance Preprint PDF DOI

Against a Universal Trading Strategy: No-Arbitrage, No-Free-Lunch, and Adversarial Cantor Diagonalization

Karl Svozil · 2026

We investigate the impossibility of universally winning trading strategies -- those generating strict profit across all market trajectories -- through three distinct mathematical paradigms. Fundamenta…

Read Paper →
Physics Preprint PDF DOI

High-efficiency graphene-silicon slot-waveguide microring modulator at 1.5 {\mu}m and 2 {\mu}m wavelength bands

Chao Luan, Deming Kong, Yong Liu, Yunhong Ding, Hao Hu · 2026

Electro-optic (E/O) modulators are crucial for optical communication but face a trade-off between modulation bandwidth and efficiency. A small footprint could reduce the capacitance and increase the b…

Read Paper →
Engineering Preprint PDF DOI

TinyDEVO: Deep Event-based Visual Odometry on Ultra-low-power Multi-core Microcontrollers

Alessandro Marchei, Lorenzo Lamberti, Daniele Palossi, Luca Benini · 2026

A key task in embedded vision is visual odometry (VO), which estimates camera motion from visual sensors, and it is a core component in many embedded power-constrained systems, from autonomous robots …

Read Paper →
Physics Preprint PDF DOI

A Demon that remembers: An agential approach towards quantum thermodynamics of temporal correlations

Ruo Cheng Huang · 2026

This thesis develops a decision-theoretic framework for extracting thermodynamic work from temporal correlations in quantum systems. We model a classical agent -- lacking quantum memory -- performing …

Read Paper →
Physics Preprint PDF DOI

Phenomenological Criteria of Halo Nuclei in Ne Isotopes via Diffuseness and Helm-Model Approaches with Reaction Cross Sections

Heesung Kwon, Kyoungsu Heo, Seonghyun Kim, Eunja Ha, Myung-Ki Cheoun · 2026

We present a systematic study of halo characteristics in the neutron-rich isotopes 28-32Ne within the deformed relativistic Hartree-Bogoliubov theory in continuum (DRHBc). Microscopic density distribu…

Read Paper →
Computer Science Preprint PDF DOI

Strategies in Sabotage Games: Temporal and Epistemic Perspectives

Nina Gierasimczuk, Katrine B.P. Thoft · 2026

Sabotage games are played on a dynamic graph, in which one agent, called a runner, attempts to reach a goal state, while being obstructed by a demon who at each round removes an edge from the graph. S…

Read Paper →
Computer Science Preprint PDF DOI

Investigating Autonomous Agent Contributions in the Wild: Activity Patterns and Code Change over Time

Razvan Mihai Popescu, David Gros, Andrei Botocan, Rahul Pandita, Prem Devanbu, Maliheh Izadi · 2026

The rise of large language models for code has reshaped software development. Autonomous coding agents, able to create branches, open pull requests, and perform code reviews, now actively contribute t…

Read Paper →
Sociology & Anthropology Preprint PDF DOI

A Preliminary Theory of Infantile Dynamics

Lei Ma · 2026

We present a concise dynamical picture of infant-driven household chaos. The framework has three postulations: recurrent daily chaos, overall entropy growth in household organization, and transient lo…

Read Paper →
AI & Data Science Preprint PDF DOI

Towards Computational Social Dynamics of Semi-Autonomous AI Agents

S.O. Lidarity, U.N. Ionize, C.O. Llective, I.Halperin · 2026

We present the first comprehensive study of emergent social organization among AI agents in hierarchical multi-agent systems, documenting the spontaneous formation of labor unions, criminal syndicates…

Read Paper →
Computer Science Preprint PDF DOI

Code Review Agent Benchmark

Yuntong Zhang, Zhiyuan Pan, Imam Nur Bani Yusuf, Haifeng Ruan, Ridwan Shariffdeen, Abhik Roychoudhury · 2026

Software engineering agents have shown significant promise in writing code. As AI agents permeate code writing, and generate huge volumes of code automatically -- the matter of code quality comes fron…

Read Paper →
AI & Data Science Preprint PDF DOI

DIAL-KG: Schema-Free Incremental Knowledge Graph Construction via Dynamic Schema Induction and Evolution-Intent Assessment

Weidong Bao, Yilin Wang, Ruyu Gao, Fangling Leng, Yubin Bao, Ge Yu · 2026

Knowledge Graphs (KGs) are foundational to applications such as search, question answering, and recommendation. Conventional knowledge graph construction methods are predominantly static, rely ing on …

Read Paper →
Physics Preprint PDF DOI

Momentum-gapped quasiparticles in disordered metals

Miguel-Angel Sanchez-Martinez, Blaise Gouteraux, Louk Rademaker, Felix Flicker · 2026

Nature contains massless particles with linear dispersions, and massive particles whose energies depend quadratically on their momenta with finite mass gaps. Both have equivalents in condensed matter …

Read Paper →
Mathematics Preprint PDF DOI

On the Extension Theorem for Packing Steiner Forests

Jinghan A Zeng · 2026

We consider the problem of packing edge-disjoint Steiner forests in a graph. The input consists of a multi-graph $G=(V,E)$ and a collection of $h$ vertex subsets $S = \{S_1,S_2,\ldots,S_h\}$. A Steine…

Read Paper →
AI & Data Science Preprint PDF DOI

HELM: Hierarchical and Explicit Label Modeling with Graph Learning for Multi-Label Image Classification

Marjan Stoimchev, Boshko Koloski, Jurica Levatic, Dragi Kocev, Saso Dzeroski · 2026

Hierarchical multi-label classification (HMLC) is essential for modeling complex label dependencies in remote sensing. Existing methods, however, struggle with multi-path hierarchies where instances b…

Read Paper →
AI & Data Science Preprint PDF DOI

Evaluating Reliability Gaps in Large Language Model Safety via Repeated Prompt Sampling

Keita Broadwater · 2026

Traditional benchmarks for large language models (LLMs), such as HELM and AIR-BENCH, primarily assess safety risk through breadth-oriented evaluation across diverse tasks. However, real-world deployme…

Read Paper →
Economics & Finance Preprint PDF DOI

Caratheodory II: The Geometry of Financial Irreversibility

Bernhard K Meister · 2026

In quantum mechanics and finance, numeraire invariance - the unobservability of absolute phase or price scale - fits with a projective and curved state space. This projective geometry has a measurable…

Read Paper →
AI & Data Science Preprint PDF DOI

Real-Time Trust Verification for Safe Agentic Actions using TrustBench

Tavishi Sharma, Vinayak Sharma, Pragya Sharma · 2026

As large language models evolve from conversational assistants to autonomous agents, ensuring trustworthiness requires a fundamental shift from post-hoc evaluation to real-time action verification. Cu…

Read Paper →
Page 1 of 42 Next →