human-computer interaction

Specializing LLMs with Custom Datasets: A Four-Round Open vs Closed Comparison

Engineering RAG Systems for Real-World Applications: Design, Development, and Evaluation

Five domain-specific RAG applications developed for real-world scenarios across governance, cybersecurity, agriculture, industrial research, and medical diagnostics are presented, highlighting technical, operational, and ethical challenges affecting the reliability and usability of RAG systems in practice.

LLM-based Multi-Agent System for Intelligent Refactoring of Haskell Code

Results highlight the ability of LLM-based multi-agent in managing refactoring tasks targeted toward functional programming paradigms and hint that LLM-based multi-agent systems integration into the refactoring of functional programming languages can enhance maintainability and support automated development workflows.

Anomaly detection in smart power grids with graph-regularized MS-SVDD: a multimodal subspace learning approach

A generalized Multimodal Subspace Support Vector Data Description model with graph-embedded regularization is proposed, illustrating how relational and structural information can be systematically embedded into one-class models, enabling robust learning under complex, high-dimensional, and multimodal conditions.

From Business Meetings to Requirement Artifacts: An Agentic AI Approach with MARARE

Preliminary results indicate performance differences across LLMs, suggesting that model choice influences coverage, consistency, and hallucination rates.

Bridging Humans and LLMs: Investigating Human-AI Collaboration in Multi-agent Requirements Analysis for Organizational AI Adoption

LLM-based multi-agent systems can support strategic AI planning by enabling iterative refinement with human experts by supporting structured and collaborative Requirements Engineering processes for AI adoption planning.

What Current AI Benchmarks Leave Unmeasured: Modality, Search, Citations, and Implications (for Safety Evaluations)

It is argued that AI safety evaluations should systematically account for modality, multi-run consistency, search conditions, and response-level behaviors to better reflect how deployed AI systems behave in practice.

Toward a Unified Security Systems Theory for Autonomous AI Systems

This paper synthesizes the findings of the five-paper AI Agent Security Series into a unified, formal, and falsifiable theory of autonomous agent security, and establishes three meta-theorems: the Component Insufficiency Theorem, the Dynamic Necessity Theorem, and the Interaction Irreducibility Theorem.

REFINE: A Multi-Agent LLM Approach for Evidence-Guided Code Refactoring

This work introduces REFINE (Refactoring with Evidence-aware Flow for Integrated ageNtic Execution), a tool-agnostic, evidence-aware multi-agent approach for generating Java file-level refactoring candidates that achieves a higher median code-smell reduction with smaller edits and fewer public-method removals.

Human Agency under Algorithmic Governance: A Humanities Framework for Law, Management and Public Life

The paper argues that algorithmic governance should not be assessed only by whether systems are accurate, explainable or compliant, but also by whether affected persons retain interpretive agency, contestatory power, relational recognition and meaningful participation in institutional life.

Do User-Authored Permission Policies Improve Protection Against AI Agent Overreach?

A mechanism in which a language model maps actions to plain-language consequence categories with user-authored"allow","ask", or"never"rules is examined, and a gap between preference and commitment is revealed: repeatedly choosing "ask" preserves case-by-case choice but prevents a standing policy from settling decisions...

A Simulator-Grounded Framework For Constructing Verifiable Muscle-Grounded QA From 3D Tongue Meshes (extended version)

A simulator-grounded construction framework, instantiated as 3DTongueQA, that shows geometry-grounded supervision supporting both unified language QA and structured prediction and shows geometry-grounded supervision supporting both unified language QA and structured prediction.