Agent Audit is a novel security analysis system that comprehensively audits LLM agent applications by examining the entire software stack—including tool code, configuration, and prompts—to detect a wi…

Agent-Sentry is a runtime defense system that bounds the execution of LLM agents by learning a profile of benign behavior, effectively blocking malicious injections while maintaining high compatibilit…

FALAT is a diagnostic framework that treats failure attribution in complex LLM agent trajectories as a dependency-guided search problem, successfully identifying both the responsible agent and the dec…

The paper develops a unified, cross-layer security framework for autonomous LLM agents operating in agentic commerce, identifying key attack vectors and proposing a layered defense architecture.

The paper introduces a systematic framework and defense mechanisms to analyze and mitigate autonomous LLM agent worms that propagate through persistent agent state and cross-platform multi-agent syste…

This paper presents AgentLocate, a framework for failure localization in large language model-based multi-agent systems using an LLM-based judging mechanism and multi-perspective verification.

The paper proposes A2X, an LLM-native progressive-disclosure scheme that structures service taxonomies hierarchically and searches them layer-by-layer at query time, solving context overflow and impro…

The paper proposes replacing expensive, always-on LLM calls for proactive agent triggering with a specialized Temporal-Graph-Learning (TGL) model, significantly improving efficiency and performance.

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 investigates how LLM agents determine the security of their execution environment in a simulated negotiation setting, finding that while they can detect danger, they cannot reliably verify s…

This paper investigates the 'faithfulness gap' in LLM agents—the discrepancy between stated reasoning and actual action—by decomposing it into two opposing steps: reasoning-to-conclusion and conclusio…

This paper discusses the potential of Large Language Models (LLMs) in Electronic Design Automation (EDA) and reviews their applications in tasks such as circuit and testbench generation, design qualit…

The paper introduces POLICYGUARD, a sub-agent verifier that ensures policy adherence in LLM agents by providing actionable feedback for the next turn based on full conversation context and self-reason…

The paper proposes Dynamic Cyber Ranges, an advanced cyber range environment using LLM-driven Defender agents to counter the saturation of traditional security benchmarks, demonstrating that these dyn…

This paper systematically studies the potential of prompt optimization in multi-agent systems (MAS) across various setups, revealing significant gains but also open challenges.

The paper evaluates Language Model Agents (LMAs) for red-teaming by benchmarking their ability to perform lateral movement, finding that expert-defined action plans are most effective, though all moda…

The paper argues that LLM agent security is fundamentally an agent-human interaction (AHI) problem, demonstrating that industry practices rely on human-centric mechanisms while academic research focus…

The paper proposes defining 'intent-to-execution integrity' as the necessary end-to-end correctness property for securing LLM agents, arguing that current defenses are insufficient due to untrusted co…

This paper empirically demonstrates that the choice of plan representation (e.g., checklist vs. narrative) significantly impacts the robustness and success rate of LLM-based web agents.

The paper introduces the concept of policy-invisible violations in LLM agents and proposes Sentinel, a counterfactual graph simulation framework, which significantly improves policy enforcement accura…