This paper studies AI development frameworks for software engineering and proposes a six-dimension process taxonomy.

COLLEAGUE.SKILL introduces an automated system that distills heterogeneous traces of human expertise and role-specific knowledge into portable, inspectable, and usable AI skill packages.

Persona prompting does not universally improve LLM performance; instead, it systematically trades increased expertise depth for reduced clarity, making multi-metric evaluation essential.

The paper introduces CAESAR, a novel multi-agent framework that coordinates LLM agents across five specialized roles to improve success rates and stability in complex, multi-stage cyber intrusion task…

The paper addresses the lack of user understanding regarding the actions and residual effects of advanced computer-use agents by proposing AgentTrace, a traceability framework for visualizing agent be…

The paper proposes a structured prompt engineering framework to enhance the integrity and reliability of Chain-of-Thought (CoT) reasoning in LLMs, demonstrating significant improvements in security-se…

The paper surveys the use of LLMs for agentic NetOps and AIOps, arguing that operational reliability depends not on the model itself, but on robust surrounding machinery and workflow-centered evaluati…

The paper proposes a secure-by-design Generative AI framework that integrates PromptShield for LLM security and CIAF for structured cloud forensic investigation, significantly improving both robustnes…

The paper introduces Rationalize, a role-pair framework that facilitates shared semantic reasoning between humans and AI models to achieve deep alignment of intent and action.

This study investigates human-AI collaboration in question answering, finding that while collaboration is beneficial, humans make suboptimal decisions by both under-relying on correct AI suggestions a…

The paper introduces CI-Work, a benchmark demonstrating that current enterprise LLM agents frequently leak sensitive information while performing tasks, suggesting that privacy protection requires arc…

The paper defines AI Identity as the correspondence between an agent's declared state and its observed behavior, concluding that current infrastructure and standards are fundamentally inadequate for g…

The paper introduces ARGUS, a defense mechanism that uses provenance-aware decision auditing to protect LLM agents from sophisticated, context-aware prompt injection attacks, significantly reducing th…

MOOSE-Copilot is a novel web-based framework that unifies scientific hypothesis discovery by formalizing human-AI interaction, significantly improving performance over autonomous LLM baselines.

The paper proposes a persona-based evaluation framework that replaces monolithic AI benchmarks with structured cognitive profiles to capture diverse human perspectives, while also identifying the chal…

Tool Forge is a validation-carrying toolchain that converts natural language capability intent into governed, sandbox-verified tool artifacts, significantly improving agent efficiency and reliability.

The paper introduces a validated, consensus-labeled prompt bank that separates requests for executable malicious code (weapons) from requests for general harmful security knowledge, providing a more g…

The paper argues that prompt injection is a fundamental vulnerability in AI agents, proposing that Contextual Integrity (CI) offers a principled framework to understand and mitigate context-sensitive…

The paper introduces STRIATUM-CTF, a modular agentic framework that uses a standardized context protocol to enable LLMs to perform multi-step, stateful reasoning for general-purpose CTF solving, achie…

The paper introduces AIBuildAI-2, a knowledge-enhanced agent that significantly improves the automatic building of AI models by integrating an external, evolving knowledge system, achieving state-of-t…