CompanyAnthropic8 recent entries28 Aug 2026FaulT-Bench: Towards Benchmarking Network Troubleshooting LLM Agents under Unreliable User TicketsarXiv:2608.27021v1 Announce Type: cross Abstract: LLM-based agents are increasingly proposed for network fault diagnosis, but existing benchmarks evaluate them only on accurate tickets and always assu→3 Sept 2026Public-Sharing Labels and Verbatim Field Egress in an MCP-to-A2A Agent Configuration: A Controlled Multi-Model StudyarXiv:2609.01693v1 Announce Type: cross Abstract: Safety properties assessed separately for Model Context Protocol (MCP) tool use and Agent2Agent (A2A) delegation need not describe behavior when one a
CompanyOpenAI7 recent entries15 Apr 2026Local-Splitter: A Measurement Study of Seven Tactics for Reducing Cloud LLM Token Usage on Coding-Agent WorkloadsarXiv:2604.12301v1 Announce Type: cross Abstract: We present a systematic measurement study of seven tactics for reducing cloud LLM token usage when a small local model can act as a triage layer in fr→7 May 2026TSCG: Deterministic Tool-Schema Compilation for Agentic LLM DeploymentsarXiv:2605.04107v1 Announce Type: cross Abstract: Production agent frameworks (OpenAI Function Calling, Anthropic Tool Use, MCP) transmit tool schemas as JSON, a format designed for machine parsing, n→26 May 2026ToolRegistry: A Protocol-Agnostic Tool Management Library for Function-Calling LLMsarXiv:2507.10593v3 Announce Type: replace-cross Abstract: Every LLM tool call is structurally an RPC -- a function name, JSON arguments, and a serialized result -- yet each protocol (native Python, MC→3 Jun 2026The Impact of Configuring Agentic AI Coding Tools on Build-vs-Buy Decisions: A Study ProtocolarXiv:2606.03907v1 Announce Type: cross Abstract: Agentic AI coding tools write code with increasing autonomy and in doing so decide when to import a library and when to implement functionality from s→26 Jun 2026The Open Source Economic Index of AI Adoption and CapabilityarXiv:2606.26118v1 Announce Type: cross Abstract: We work towards measuring both AI adoption and the capability of AI to perform discrete labor tasks across various occupations. To measure adoption, w→20 Aug 2026Flama: a Python framework for development and deployment of production-ready APIs, machine learning, and LLM servicesarXiv:2608.18733v1 Announce Type: cross Abstract: We present Flama, an open-source Python framework for developing and deploying production-ready web APIs, machine learning services, and large-languag→30 Sept 2026MCP Error Messages Written for Developers Hurt the Most Capable Agents MostarXiv:2609.35381v2 Announce Type: replace-cross Abstract: Many Model Context Protocol (MCP) servers wrap web APIs built for human developers, and their error messages tell the reader to run a command,
CompanyGoogle8 recent entries25 May 2026Are Frontier LLMs Ready for Cybersecurity? Evidence for Vertical Foundation Models from Dual-Mode Vulnerability BenchmarksarXiv:2605.23243v1 Announce Type: cross Abstract: We evaluate whether frontier LLMs are ready for cybersecurity through a dual-mode benchmark: white-box function-level vulnerability detection (VulnLLM→26 May 2026ToolRegistry: A Protocol-Agnostic Tool Management Library for Function-Calling LLMsarXiv:2507.10593v3 Announce Type: replace-cross Abstract: Every LLM tool call is structurally an RPC -- a function name, JSON arguments, and a serialized result -- yet each protocol (native Python, MC→9 Jun 2026VATS: Exploiting Implicit Authority in Error-Path Injection via Systematic MutationarXiv:2606.07992v1 Announce Type: new Abstract: As the Model Context Protocol (MCP) standardizes tool-calling for autonomous agents, it introduces a critical, unexamined attack surface: the error-hand→11 Aug 2026LLM within MCP Matters: Measuring Inefficient Resource Utilization Driven by LLMsarXiv:2608.08467v1 Announce Type: new Abstract: The Model Context Protocol (MCP) standardizes how servers expose data and tools to Large Language Models (LLMs). A common server design embeds frequentl→1 Sept 2026T-MAP: Red-Teaming LLM Agents with Trajectory-aware Evolutionary SearcharXiv:2603.22341v2 Announce Type: replace-cross Abstract: While prior red-teaming efforts have focused on eliciting harmful text outputs from large language models (LLMs), such approaches fail to capt→9 Sept 2026How Long Until Your Robot Ignores You? A Safety Benchmark for LLM Orchestrators in Human-Humanoid CollaborationarXiv:2609.07288v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly employed to orchestrate robot behavior through natural-language interfaces, yet no benchmark exists to eva→15 Sept 2026AcquireBound: Runtime Authorization for Resources Acquired by AI AgentsarXiv:2609.14744v1 Announce Type: new Abstract: By acquiring compute, credentials, accounts, services, and other agents, autonomous AI agents can introduce new authority into a task. Payment, budget, →12 Oct 2026APEX-Harm: Evaluating Agent Safety in Shared Professional WorkspacesarXiv:2610.13623v1 Announce Type: cross Abstract: Professional agents increasingly work through command-line interfaces and multiple tools over shared workspaces containing files, messages, and busine
CompanyMeta8 recent entries6 Aug 2026Diagnosing Tool-Selection Reasoning in LLM Agents with Canary ToolsarXiv:2608.04719v1 Announce Type: new Abstract: Agent evaluations tell us that a model picked the wrong tool, but rarely why. We introduce canary tools: diagnostic probe tools planted in an agent's Mo→24 Aug 2026Nexus: Depth-Adaptive KV-Cache Splicing and Retrieval-Decoupled Tool Routing for Agentic LLMs on Unified MemoryarXiv:2608.20397v1 Announce Type: new Abstract: Agentic large language models (LLMs) on the Model Context Protocol (MCP) re-encode verbose tool schemas every turn, so prefill - quadratic in sequence l→26 Aug 2026Hybrid Semantic Tool Discovery for Enterprise MCP Gateway: Architecture and ImplementationarXiv:2608.23992v1 Announce Type: cross Abstract: Large language model (LLM) agents invoke external tools to retrieve and reason over information beyond pretrained knowledge. The Model Context Protoco→10 Sept 2026AgentBrew: Offline Tool-Use Agent Learning from Raw Real-World TrajectoriesarXiv:2609.05837v1 Announce Type: new Abstract: LLM-based agents are increasingly deployed in real-world applications through tool-use APIs, yet training them for specific environments remains fundame→12 Sept 2026An Agentic Evaluation Framework for AI-Generated Scientific Code in PETScarXiv:2603.15976v2 Announce Type: replace Abstract: While LLMs have accelerated scientific code generation, comprehensively evaluating generated code remains challenging. Many benchmarks emphasize fun→15 Sept 2026AutoTailor: Automatic, User-Aligned Capability Selection and Adaptation for Web AgentsarXiv:2609.13548v1 Announce Type: new Abstract: Web agents can utilize reusable tools to reduce the cost and latency of low-level browser interaction, but automatically discovered tool collections can→2 Oct 2026Tokenized Key-Gated Adapter Routing: A Secure Access Control Mechanism Against Private Data Leakage in LLMsarXiv:2610.00309v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in privacy-critical domains (e.g., healthcare, finance, and government), but their propensity t→2 Oct 2026Measuring the Microtask Eligibility Gap: When Is an Off-the-Shelf SLM Enough for an Agent Harness?arXiv:2610.00025v1 Announce Type: new Abstract: Agent harnesses increasingly want to run small language models (SLMs) on the microtasks around a frontier large language model (LLM) planner: auto-appro
CompanyMistral2 recent entries7 Jul 2026Governed MCP: Kernel-Level Tool Governance for AI Agents via Logit-Based Safety PrimitivesarXiv:2604.16870v2 Announce Type: replace-cross Abstract: AI agents increasingly call external tools (file system, network, APIs) through the Model Context Protocol (MCP). These tool calls are the age→25 Sept 2026Persistent Billable State: Denial-of-Wallet Attacks and Defenses in Tool-Calling LLM AgentsarXiv:2609.28585v1 Announce Type: cross Abstract: Multi-step tool-calling LLM agents rely on host runtimes to preserve state across turns. When a runtime carries an external tool return into later mod
CompanyxAI2 recent entries23 Sept 2026PhysAI-Bench: A Benchmark for LLM-Based Agentic Decision-Making in Autonomous UAV-Centric Physical AIarXiv:2609.23695v1 Announce Type: new Abstract: Recent advances in Physical AI have accelerated the use of foundation models in autonomous systems such as unmanned aerial vehicles (UAVs), which must p→30 Sept 2026Auditable Long-Term Memory: A Deterministic Retrieval Chain Measured at 479/475 of 500 on LongMemEval-SarXiv:2609.38021v1 Announce Type: cross Abstract: We evaluate an auditable long-term memory system on LongMemEval-S. Its retrieval chain uses hybrid candidate retrieval, cross-encoder reranking, cover
CompanyDeepSeek5 recent entries27 May 2026Device Context Protocol: A Compact, Safety-First Architecture for LLM-Driven Control of Constrained DevicesarXiv:2605.26159v1 Announce Type: cross Abstract: Large language models are increasingly used as orchestrators of external tools via the Model Context Protocol (MCP), but MCP is built for software ser→28 May 2026TCP-MCP: Landscape-Guided Co-Evolution of Prompts and Communication Topologies for Multi-Agent SystemsarXiv:2605.27850v1 Announce Type: new Abstract: Effective multi-agent systems cannot be designed by selecting prompts or communication graphs in isolation. Agent behavior depends on the information an→25 Jun 2026Verifiable Manifest Signing and Transparency Enforcement for Secure MCP-Based LLM PipelinesarXiv:2601.23132v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly deployed in tool-driven environments such as healthcare analytics, financial systems, retrieval-→7 Aug 2026Hardware Keystores for AI Agent Signing Workflows: A Zero-Trust MCP Enforcement ArchitecturearXiv:2608.06130v1 Announce Type: cross Abstract: AI agents performing cryptographic operations (signing Git commits, authenticating API calls, issuing certificates) currently store private keys in so→2 Oct 2026Finding the Right Fit: Model-Harness Interactions across Agent TasksarXiv:2610.00917v1 Announce Type: new Abstract: Choosing an agent system means choosing both a language model and the harness through which it acts. We ask whether a strong model, harness, or pairing
CompanyNVIDIA1 recent entries7 May 2026When Agents Handle Secrets: A Survey of Confidential Computing for Agentic AIarXiv:2605.03213v1 Announce Type: cross Abstract: Agentic AI systems, specifically LLM-driven agents that plan, invoke tools, maintain persistent memory, and delegate tasks to peer agents via protocol