This paper introduces tap, a file-based collaboration protocol enabling LLM agents from different vendors to collaborate on a shared codebase without shared memory or identical runtimes.

The paper introduces MAAD, a multi-agent framework that autonomously transforms software requirements into comprehensive, multi-view architectural blueprints, significantly improving completeness and…

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

The paper proposes Multi-Agent Computer Use (MACU) systems, which significantly improve performance on complex, long-horizon tasks by enabling parallel execution and dynamic task decomposition compare…

The paper introduces Language-Based Agent Control (LBAC), a new programming model that extends static typing and runtime enforcement guarantees to agentic applications, ensuring that agent-generated c…

This paper introduces ASE-26, a comprehensive undergraduate curriculum designed to formalize and teach agentic software engineering as a distinct academic discipline.

The paper proposes an empowerment-guided multi-agent system that uses semantic checkpoints and structured communication to ensure that complex scientific computing workflows maintain semantic consiste…

This paper presents EurekAgent, an environment-engineered agent system for metric-driven autonomous scientific discovery.

This paper investigates the scaling behavior of homogeneous LLM-driven Multi-Agent Systems (MAS) and finds that performance exhibits diminishing returns due to coordination overhead, rather than scali…

The paper proposes a modular agent framework and novel learning methods to design and optimize practical, cost-effective, and controllable LLM-based agentic systems.

This paper analyzes the security of LLM-based autonomous agents by drawing parallels to operating system security, finding that while some vulnerabilities are inherent, many can be mitigated using est…

The paper argues that current 'on-the-fly' AI agent design lacks necessary software engineering rigor and proposes an 'AI Workflow Store' to provide hardened, reusable, and reliable agent workflows.

The paper proposes Meta-Team, an experience-driven framework that enables multi-agent systems (MAS) to collaboratively self-evolve by transforming complex execution experiences into reusable improveme…

The paper experimentally evaluates 12 multi-agent LLM collaboration topologies for software design, finding that structural adversarial prompting and cross-model review are the most effective approach…

This paper proposes a role-based agentic workflow for vulnerability analysis and mitigation in software engineering, integrating an analyzer agent with CodeQL and evaluating its performance on 25 real…

This paper provides the first comprehensive security analysis of the Agent Skills framework, identifying severe structural vulnerabilities that require fundamental architectural changes rather than si…

Agent libOS introduces a library-OS-inspired runtime substrate that treats LLM agents as schedulable processes, providing explicit capability control and robust auditing for long-running, stateful age…

The paper introduces the concepts of Agentic Technical Debt and Stochastic Tax to categorize and manage the unique governance and operating liabilities inherent in complex, multi-step AI agent systems…

The study compares agentic data retrieval using unstructured web data versus structured, semantically-annotated datasets, concluding that semantic metadata remains essential for high-precision, reliab…

The paper introduces a comprehensive security framework, AgentRFC, to systematically analyze and test the security conformance of various AI agent protocols, identifying critical design gaps, especial…