The paper introduces FORGE, a feedback-driven execution system that improves LLM-based binary analysis by interleaving reasoning and tool interaction, achieving high-quality vulnerability discovery on…

The paper introduces Sovereign Agentic Loops (SAL), a control-plane architecture that decouples LLM reasoning from system execution to enhance safety and reliability in real-world AI agents.

The paper introduces Harness-Bench, a diagnostic benchmark that measures how different system 'harnesses' affect LLM agent performance in realistic workflows, showing that agent capability must be rep…

This paper proposes HCP, a Handle-Capability Protocol runtime for MCP-style agent systems, which implements eight execution-control invariants to enhance security while preserving MCP-like workflows.

The paper proposes the Intelligent Computing Architecture Model (ICAM), a six-layer framework that unifies disparate concepts in model-native computing by viewing the LLM stack through a dual-plane ar…

The paper argues that web agents should abandon the reactive ReAct paradigm in favor of a plan-then-execute approach, which requires developing typed, task-level APIs to properly structure web interac…

LEAF is a dynamic analysis framework for Rust that captures MIR-level semantic information and delivers it as an event stream through Dynamic MIR.

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 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…

The paper introduces SABER, a new benchmark that evaluates the operational safety of LLM coding agents in complex, stateful project environments, finding that current models have a high rate of harmfu…

This paper evaluates the performance of large language models on popular benchmarks and finds that only a small percentage of the performant implementations are significantly faster than canonical sol…

The paper introduces LACUNA, a novel programming model that allows LLM agents to write code that shapes the runtime environment while maintaining strong type-checking safety guarantees.

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 the Communicating Finite Automata (CFA) abstraction and a framework for component program refactoring in large language model inference services, achieving significant speedup and r…

The paper presents a tool-making pipeline for production LLM agents that compiles repeated steps into validated, versioned tools before deployment, reducing latency and error rate.

The paper introduces OpenClawBench, a large-scale dataset and framework for measuring process-side anomalies in real-world agent execution trajectories, demonstrating that task success does not guaran…

This paper proposes an organizational memory for LLM-based agents to access and share enterprise-specific procedural knowledge for reliable business process execution.

The paper introduces Hyperparam, a set of lightweight JavaScript libraries designed to enable direct, model-aware querying of unstructured data (like agent traces) within client-side AI applications.