관심도 점수
100
- 검색 slug
- mcp
- 실제 연결
- Hacker News, GitHub, arXiv
- 키워드
- and, the, for, with, mcp, agent, model, tool
- 마지막 수집
- 2026-11-21T07:12:14.552Z
출처별 탭
Monte Carlo Pass Search for Setpieces
Set pieces produce about a third of non-penalty expected goals (xG), yet they are usually evaluated by what happened next. We present Monte Carlo Pass Search (MCPS) for set pieces, which treats a corner or a lofted free kick as a distribution over plausible executions and plausible futures instead of a single realised event. From the pre-kick state, MCPS proposes counterfactual deliveries and counterfactual set-ups (where the attackers stand at the kick), plays each out many times in a world model (3D ball physics...
FinVeriQA: Financial Research Agents for Question Answering: Routing, Retrieval, MCP Tool Use, and Provenance-Aware Evidence Verification
Large language models (LLMs) write fluent financial analyses but miscompute ratios, recall stale prices, and route questions to the wrong tool with high confidence. We ask which component should do each job in a financial question-answering assistant, and study it with FinVeriQA, an open-source multi-agent research prototype over SEC filings and live market data: a compact typed-decision model (Laya) routes each question and screens out advice requests, Python computes every number, retrieval and tools fetch evide...
Isabelle Pool Server: a pooled verification service for prover training and multi-agent proving
Isabelle Pool Server (IPS), a verification service with a pool of warm headless Isabelle sessions behind an HTTP API, with session leasing and reclamation, memory-aware admission control, and a time budget on every call. Its verification interface spans single-step execution, block-level proof checking and whole-theory builds, with checkpoints for cheap branching and backtracking, and a build from scratch as the final arbiter. The service runs as a single container with monitoring and is accessible via a Python cl...
Weighing the Envelope: Component Weight and Arbitration in Envelope-Layer Defenses for a Single LLM Agent
The envelope layer is the channel through which malicious content enters an LLM agent. Prior work established label and memory effects on multi-agent A2A envelopes, but the weight structure when MCP tools and memory coexist in a single agent remains unclear. Our threat model assumes an attacker pre-plants a malicious tool and poisons long-term memory; a benign user request inadvertently triggers it, and the attacker never enters the conversation. Following GDA Measurement and A/B/C/D, we measure how labels, memory...
Foundation Model-Driven Agentic AI for 6G
Mobile networks are outgrowing manual tuning: parameters multiply, services diversify, and traffic shifts faster than experts can react. The machine learning (ML) models that automate radio control are narrow: each is trained for one task, degrades when conditions move, and needs specialist retraining. This article introduces FM-in-the-loop, a framework for 6G radio access networks in which a foundation model (FM) reasons while lightweight machine learning agents act. It reads operator intents in plain language, d...
Millicharged Fermions as Dark Matter: Theoretical Modeling and Experimental Detection
Fermions with a small effective charge, $\qeff\ll1$, arise from kinetic mixing between an unbroken (or nearly unbroken) dark $U(1)'$ and electromagnetism, or from a genuinely fractional charge. Millicharged particles (mCPs) inherit the Pauli-exclusion constraints on fermionic dark matter (DM) in galaxies, while adding a long-range plasma phenomenology absent for neutral candidates. This review connects three strands: (i) the symmetry structure, cosmology and astrophysical bounds of millicharged fermions, comparing...
Can You Undo It? Reversibility Classes for AI Agent Actions
Tool-using AI agents change files, databases, access rights and public information, yet permission to call a tool does not establish whether a mistake can be undone. We present Reversibility Classes, a declared five-level vocabulary with argument-sensitive rules, conservative defaults and an explicit prior-state capture contract. The pinned implementation and evidence-linked registry cover 536 tools across 20 MCP servers. All 738 rule-case checks conform to declared expectations, while native annotation mapping di...
When Tool Names Are Not Identities: Measuring Provider Misbinding in MCP-Based AI Agents
Large language model (LLM) applications increasingly act as agents that select and invoke external tools. The Model Context Protocol (MCP) standardizes this interaction by allowing clients to compose tools advertised by multiple servers. However, tool metadata used for discovery and selection is not, by itself, necessarily bound to a verified provider identity. This paper studies this gap as tool-provider misbinding: a failure in which a request intended for a legitimate provider is instead resolved to an attacker...
Generating a simple silicon detector simulation with an open-weight large language model
Recent LLM developments have seen AI-generated code become commonplace in the software development industry. Without tool access, LLMs cannot execute simulations, and their knowledge of toolkits such as Geant4 is limited. We demonstrate here, a detector simulation workflow with a Qwen3.6-27B model with Q4_K_M GGUF quantisation together with custom resources and tools served via MCP servers to generate a particle detector simulation. In 50 independent runs, 42(29--56)% at 95% CI produced energy-deposit distribution...
Linglong Agent Service: A Runtime for Centralized Agent Reasoning and Distributed Execution
LLM agents can use remote tools and cloud sandboxes, but integrating reasoning, session state, and heterogeneous execution sites remains a runtime design problem. We present Linglong Agent Service (agentsvc), a self-hosted HTTP service and embeddable Python runtime that treats execution site as a configurable dimension alongside model, tools, and context. A parent service retains inference orchestration, tool descriptions, and conversation history; each inference request selects one child environment for file, she...
morluto/rea
Reverse engineer anything with agents, from app behavior down to native binaries.
Graphify-Labs/graphify
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
paperclipai/paperclip
The open-source app everyone uses to manage agents at work
affaan-m/ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
farion1231/cc-switch
A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode,DeepSeek Harness and more. Only official website: ccswitch.io
browser-use/browser-use
Open-source Python library for AI browser agents, plus Browser Use Cloud: stealth browsers and a hosted agent API.
open-webui/open-webui
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
langgenius/dify
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
n8n-io/n8n
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
Snailclimb/JavaGuide
Java 面试 & 后端通用面试指南,覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发