ToolClaude Code8 recent entries9 Oct 2026Arbiter: Detecting Interference in LLM Agent System PromptsarXiv:2603.08993v2 Announce Type: replace-cross Abstract: System prompts for LLM-based coding agents are software artifacts that govern agent behavior, yet lack the testing infrastructure applied to c→9 Oct 2026AgentTime: Can Agents Estimate and Control Their Own Runtime?arXiv:2610.09944v2 Announce Type: replace Abstract: An essential control of AI agents is their ability to manage runtime. This ability requires a sense of time-awareness, to predict and estimate wall-→
ToolCursor8 recent entries17 Sept 2026AgentPack: A Dataset of Code Changes, Co-Authored by Agents and HumansarXiv:2509.21891v3 Announce Type: replace-cross Abstract: Fine-tuning large language models for code editing has typically relied on mining commits and pull requests. The working hypothesis has been t→21 Sept 2026Reviser: Revision-Capable Text Generation via Autoregressive Cursor ActionsarXiv:2609.20830v1 Announce Type: new Abstract: Revision-capable generation is appealing because it can insert or revise earlier content, but many non-autoregressive and edit-based approaches obtain t→22 Sept 2026Omni2Web: Benchmarking Audiovisual Website DevelopmentarXiv:2609.23417v1 Announce Type: cross Abstract: Screen-recorded web editing requests contain weak deictic expressions such as ``this'' and ``there,'' whose referents depend on speech, cursor traject→22 Sept 2026Defusing Explosive Prompts: Understanding and Preventing Trigger-Based Prompt Injections in LLM AgentsarXiv:2609.22510v1 Announce Type: cross Abstract: As LLM applications integrate with external tools, they are increasingly exposed to indirect prompt injection (IPI), where adversarial instructions ar→1 Oct 2026DrivingBench: Can Vision-Language Models Drive a Toyota Corolla?arXiv:2609.38948v1 Announce Type: cross Abstract: Frontier models excel at many digital benchmarks, yet their ability to drive a real car, an everyday human skill, remains largely untested. We present→1 Oct 2026Approval Laundering: Systematizing Approval--Execution Binding Failures in AI Coding-Agent HarnessesarXiv:2609.38983v1 Announce Type: cross Abstract: Modern AI coding-agent harnesses (Claude Code, Codex CLI, Cursor) rest their security boundary on a largely unexamined assumption: that the action A a→8 Oct 2026From Retrieval to Customer Context: Evaluating Frontier-Model Systems for Voice-of-Customer AnalysisarXiv:2610.09375v1 Announce Type: new Abstract: Organizations increasingly use frontier language models to analyze customer feedback, but answer quality also depends on how that feedback is organized →12 Oct 2026AutoIndexer: Flexible-Order Decoding by Training Causal Models on Chains of EditsarXiv:2610.12545v1 Announce Type: cross Abstract: Autoregressive decoding is less suited to non-causally ordered data, e.g., cross-references or future dependencies, since their outputs cannot be revi
ToolLangChain8 recent entries30 Jun 2026Capability Gates Are Not Authorization: Confused-Deputy Failures in LLM Agent FrameworksarXiv:2606.28679v1 Announce Type: cross Abstract: Tool-using LLM agents increasingly read untrusted content while holding side-effecting tools such as payments, email, CRM, and infrastructure APIs, ye→30 Jun 2026An Agentic AI Pipeline for Appliance-Level Energy Anomaly Detection and LLM-Driven RecommendationsarXiv:2606.28467v1 Announce Type: cross Abstract: Appliance-level energy monitoring in office buildings produces noisy alerts that non-expert facility managers struggle to use. This paper proposes an →8 Jul 2026SecureCode: A Production-Grade Multi-Turn Dataset for Training Security-Aware Code Generation ModelsarXiv:2512.18542v3 Announce Type: replace-cross Abstract: AI coding assistants produce vulnerable code in 45% of security-relevant scenarios~ite{veracode2025}, yet no public training dataset teaches b→24 Jul 2026GuardianAgentBench: Where Agents Fail and How to Guard ThemarXiv:2607.20982v1 Announce Type: new Abstract: As large language model agents increasingly operate autonomously with access to tools and external environments, ensuring their safe and reliable behavi→28 Jul 2026Energy Constrained Hierarchical Underwater Monitoring via Local Multi-Agent RAGarXiv:2607.24313v1 Announce Type: cross Abstract: Marine life monitoring is limited by strict energy constraints, poor underwater connectivity, and the high cost of transmitting raw multimodal data fr→26 Aug 2026The Empire, Long Divided, Must Unite: Architectural Convergence in Three LLM Agent HarnessesarXiv:2608.23953v1 Announce Type: cross Abstract: An agent harness is what turns a language model into an autonomous agent: the surrounding code that builds the model's context, mediates its tools, ru→26 Aug 2026RENDER: Controlling Reader-Facing Evidence in LLM Memory EvaluationarXiv:2608.23568v1 Announce Type: new Abstract: Memory and RAG evaluations often treat the answering model's input as an implementation detail, even though systems may render the same history as a mem→15 Sept 2026Translating the Translator: Decomposing the Cost of English-Forced Inter-Agent CommunicationarXiv:2609.15079v1 Announce Type: cross Abstract: Multi-agent LLM architectures, such as LangChain and AutoGen, largely assume English as the lingua franca for internal inter-agent communication, even
ToolOllama8 recent entries15 Sept 2026ShopEase: A Generative AI-Based Multi-Agent Framework for Intelligent Enterprise Customer Support Using Hybrid Retrieval-Augmented GenerationarXiv:2609.13856v1 Announce Type: new Abstract: Enterprise customer support systems must answer customer questions correctly, retrieve the right policy information, use customer context, and pass diff→15 Sept 2026Context-Dependent Affordance Reports in Vision-Language ModelsarXiv:2603.04419v3 Announce Type: replace-cross Abstract: Vision-language models produce different object and use descriptions under different persona prompts, but low overlap alone does not identify →17 Sept 2026PentestChain: A Cost-Aware, MCP-Orchestrated Framework for Automated Penetration Testing with Free-Tier LLMsarXiv:2609.18120v1 Announce Type: cross Abstract: AI-driven penetration testing has been demonstrated with premium frontier models such as GPT-4, but the per-engagement token cost makes continuous, au→23 Sept 2026Measuring the Serving Stack Instead of the Model: Hidden Confounds in Local Tool-Use EvaluationarXiv:2609.26693v1 Announce Type: new Abstract: A coding agent must emit a valid tool call--a parseable invocation of a tool in the provided schema--before the harness can execute its chosen action. W→28 Sept 2026Energy Efficiency of Locally Deployed LLMs: A Preliminary Quantitative GPU Power Benchmark on Consumer HardwarearXiv:2608.00008v2 Announce Type: replace Abstract: The local deployment of large language models (LLMs) is gaining traction due to privacy concerns and the desire for on-premise inference. However, t→2 Oct 2026Mingbird: A Local-First Agent Harness Enabling Small Open Models to Complete Real TasksarXiv:2610.02001v1 Announce Type: new Abstract: Small open-weight models (2-9B) run on ordinary laptops, but under cloud-scale agent harnesses they rarely complete real tasks: tool prefill overflows t→5 Oct 2026ZeBROD: Zero-Retraining Based Recognition and Object Detection FrameworkarXiv:2512.04888v4 Announce Type: replace Abstract: Object detection constitutes the primary task within the domain of computer vision. It is utilized in numerous domains. Nonetheless, object detectio→5 Oct 2026On-Premises Multi-Course RAG Tutoring for Business Education: Hardware-Software Trade-offs in a Campus AI TutorarXiv:2610.02510v1 Announce Type: new Abstract: Campus AI tutors based on retrieval-augmented generation (RAG) must ground answers in assigned course materials while keeping textbooks and student dial
ToolVercel AI8 recent entries24 Sept 2026Training Intelligent Voice Assistant Wakeup with Controllable Synthetic ConversationsarXiv:2609.27037v1 Announce Type: new Abstract: Wake word detection is a critical component of virtual assistants, serving as the gateway to seamless user interactions. This paper introduces a novel w→24 Sept 2026A Non-Invasive Cloud-Based Migration Strategy for Post-Quantum Cybersecurity in Smart HVAC Systems: Architecture, Implementation, and Empirical EvaluationarXiv:2609.27828v1 Announce Type: cross Abstract: Legacy smart HVAC controllers rely on vendor-cloud TLS secured by ECDH and RSA, both broken by Shor's algorithm, and typical 10-15 year lifespans mean→28 Sept 2026Cartograph: Federated Tool Discovery with Operator-Attested Retrieval for AI AgentsarXiv:2609.30293v1 Announce Type: cross Abstract: The Model Context Protocol (MCP) enables AI agents to discover and call tools, but loading every definition becomes expensive as connected catalogs gr→28 Sept 2026Bridging LLM Agents and Data Spaces: An Architectural Mediation Approach using the Model Context ProtocolarXiv:2609.30341v1 Announce Type: new Abstract: Data Spaces enable sovereign and governed data sharing across organizational boundaries, but their integration with AI agents remains challenging due to→28 Sept 2026A Safety-Bounded SDC-to-MCP Gateway for Medical AI AgentsarXiv:2609.31358v1 Announce Type: cross Abstract: The Model Context Protocol (MCP) provides a common interface through which AI applications discover and use external resources and tools. It allows la→2 Oct 2026Fault-Tolerant Budget Conservation in Distributed Multi-Agent DelegationarXiv:2610.00349v1 Announce Type: new Abstract: Resource limits are becoming an authorization boundary for AI agents that delegate work across concurrent and failure-prone workers. Parent-child alloca→5 Oct 2026On-Premises Multi-Course RAG Tutoring for Business Education: Hardware-Software Trade-offs in a Campus AI TutorarXiv:2610.02510v1 Announce Type: new Abstract: Campus AI tutors based on retrieval-augmented generation (RAG) must ground answers in assigned course materials while keeping textbooks and student dial→6 Oct 2026RepTC: Representation-Aware Optimization for Efficient Traffic Classification on Edge IoT DevicesarXiv:2610.04784v1 Announce Type: cross Abstract: Traffic classification (TC) is crucial to secure Internet of Things (IoT) networks, whose edge nodes often operate under privacy, bandwidth, and energ
ToolHugging Face8 recent entries1 Oct 2026Hyperspectral Image Dataset for Benchmarking on Salient Object DetectionarXiv:1806.11314v3 Announce Type: replace Abstract: Many works have been done on salient object detection using supervised or unsupervised approaches on colour images. Recently, a few studies demonstr→1 Oct 2026dattri-LLM: A Unified and Efficient Library for Training Data Attribution at LLM ScalearXiv:2609.38767v1 Announce Type: cross Abstract: Training data attribution (TDA) estimates the contribution of individual training examples to model outputs. Most scalable TDA methods rely on per-exa→2 Oct 2026Video-Index: A Curated Meta-Benchmark for Video UnderstandingarXiv:2610.00960v1 Announce Type: new Abstract: A video benchmark should reward the capability it claims to measure, yet models can exploit answer options, question text, or partial visual evidence. W→2 Oct 2026Permutation-Robust Decision Modeling with Candidate-Independent Block-Causal AttentionarXiv:2610.01601v1 Announce Type: cross Abstract: Decision models often score a variable-sized set of candidate actions encoded in a single sequence. This setting is increasingly relevant for System 1→2 Oct 2026Mean field games as a tool for AI safety: a worked example from the July 2026 Hugging Face incidentarXiv:2610.00902v1 Announce Type: cross Abstract: One way to make AI systems safe is to shape what the system is: its objective and dispositions. We take a complementary route: treat the agents' chara→7 Oct 2026HARL-A: An Extensible Benchmark Framework for Heterogeneous Multi-Agent Adversarial Reinforcement Learning in IsaacLabarXiv:2510.01264v2 Announce Type: replace Abstract: Progress in adversarial multi-agent reinforcement learning (MARL) for robotics has been hampered by a lack of shared, extensible infrastructure that→8 Oct 2026PrismSSL: One Interface, Many Modalities; A Single-Interface Library for Multimodal Self-Supervised LearningarXiv:2511.17776v2 Announce Type: replace Abstract: We present PrismSSL, a Python library that unifies state-of-the-art self-supervised learning (SSL) methods across audio, vision, graphs, and cross-m→9 Oct 2026From Reactive Containment to Proactive Assurance: Lessons from OpenAI, Anthropic, and Google Agent Security IncidentsarXiv:2610.12463v1 Announce Type: cross Abstract: In 2026, cybersecurity evaluations involving OpenAI, Anthropic, and Google agents reached real systems outside their authorized test scope. The paths