small language model

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.

Clean Attacks: Formalizing Semantically Valid Adversarial Behavior in Autonomous AI Agent Systems

A previously unstated class of adversarial input called a clean attack - an input that is syntactically correct, semantically consistent with the declared task context, consistent with all observable policy constraints and still has the goal of misguiding the agent away from the original operator goal - is identified a...

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.

Secure AI Systems Protecting Machine Learning Models from Emerging Cyber Threats

Securing AI systems is not a task any single discipline can accomplish alone; it requires sustained collaboration between machine learning researchers, cybersecurity professionals, and policymakers if AI technologies are to remain reliable, trustworthy, and resilient in adversarial environments.

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.

HEPToolBench 1.2: Testing How Reliably Language Models Can Drive Particle Physics Software

HEPToolBench is introduced, a benchmark of 28 collider-simulation tasks scored by deterministic, task-specific scorers, plus a three-task structured-debugging extension, and moving syntax generation into deterministic software can substantially improve reliability for both small local and frontier models.

The Story Shapes the Agent: Narrative Priors in LLM Behavior

It is suggested that LLM behavior that survives narrative changes should be grounded in concrete actions rather than abstract descriptions, and that persona effects that do transfer across narratives arise from behavioral anchors, persona descriptions whose language maps directly onto shared actions.

Evaluating Large Language Models’ Ability to Reason About Anatomical Spatial Relations

Benchmarking the Benchmarks: Evaluating Automated Safety Benchmarks for Small Language Models

A large-scale assessment of the effectiveness and robustness of these automated pipelines is conducted by evaluating five widely used benchmark suites across 26 open-source SLMs under a unified judging rubric, which reveals a capability-safety confound that mixes model capability with apparent safety.

Whose Cost Is the Demon's? Five People Put It in Five Places ── Measurement, Observation, Erasure, Room: Irreversible Gates Do Not All Lose the Same Amount, AND Losing 1.188722 Bits and XOR Exactly 1.000000 ── [Paper 248]

For more than a century Maxwell's demon has been asked where the cost lies. What this paper counts is not the answer but where the cost was placed: five people put it in five different places. And once numbers are put in, the statement that an irreversible gate pays one bit turns out to be wrong as well. No new mathema...

VisGuard-Ur: A Proof-of-Concept Study on Typographic Jailbreak and Prompt-Injection Attacks Against Urdu-Aware Vision-Language Models

Vision-language models (VLMs) are increasingly deployed as document- and image-understanding agents, yet published safety evaluations of these systems are almost exclusively conducted in English plain text. This leaves two attack surfaces largely unexamined for low-resource languages: (1) adversarial instructions embed...

Integration of Cultural Literacy in the Development of Listening Skills Teaching Materials in BIPA Learning

Abstract This study aims to develop listening skills teaching materials in the Indonesian Language for Foreign Speakers (BIPA) course based on cultural literacy for seventh-semester students of the Indonesian Language and Literature Education Study Program at PGRI Silampari University in the 2025/2026 academic year. T...