Explore tools, prompts, skills, news and resources related to LLM 第3页.
Prompt works related to LLM 第3页
Latest articles, prompts, use cases and editorial content about LLM 第3页
MoEngage built Merlin AI, a set of AI agents on Amazon Bedrock AgentCore, to let marketing teams manage campaigns via natural language. They exposed existing OpenAPI APIs as MCP tools, with tenant isolation and JWT auth....
Lambda is deploying NVIDIA Photonics co-packaged optics (CPO) switches to connect over 10,000 GPUs in GB300 NVL72 racks, achieving lower power, higher reliability, and reduced latency. Tests show up to 5x better power ef...
Researchers proposed LACCO, a two-stage algorithm for training language models across low-bandwidth networks. It overlaps global communication with local computation while using globally aggregated updates shared by ever...
WebArena-Pro is a new benchmark for web agents comprising 300 tasks across 20 self-hosted web applications in six domain categories. It extends evaluation beyond text and vision by treating audio and video as core observ...
Meta has moved JiTTests from a research prototype into its internal production infrastructure. The system uses LLM-generated just-in-time tests to prove risky code diffs change behavior before they land. Meta reports cat...
Researchers introduced OutfitterBench, a benchmark that asks LLM agents to manage an outdoor-equipment rental business for 200 days under a fixed capital ceiling. The environment includes a 46-product catalog and roughly...
The paper introduces Symbolic Swapper, an LLM-based adversarial attack model that automatically generates obfuscated planning domains with non-standard symbolic vocabularies. It evaluates whether strong reasoning LLMs re...
Researchers introduce Soteria, a framework for LLM agents that performs multi-step tool calls while satisfying both task completion and domain policy conformance. Before execution, the agent generates a structured plan t...
The paper argues that world-model video encoders such as V-JEPA encode scene dynamics (direction, speed, order, state) in a subspace shared across videos, while frame-wise text-aligned encoders like SigLIP do not, and th...
An arXiv study investigates why alignment training on individual LLM agents fails to transfer to multi-agent settings across software-engineering and consulting-proposal tasks. It finds that diffusion of responsibility s...
The paper presents G-CAST, a governed continual self-training system for LLM-powered e-commerce shopping agents that must adapt as user demand drifts and the agent's tools, skills, and procedures evolve. G-CAST conv...
Researchers introduce CarryOn, a lightweight context manager for long-horizon LLM agents that pairs compact execution state with fine-grained, source-linked evidence. A learned selector and adaptive retention policy keep...
Researchers propose Vision-as-a-Tool, a paradigm that treats multimodal large language models as callable external utilities for visual reasoning. They implement the idea in VHarness, a framework built around five atomic...
Cmpnd has released dspy-wsp, an MIT-licensed prototype that packages weight-space programming as a DSPy optimizer called WeightSpace, which plugs into existing DSPy programs and metrics. A frontier writer LLM reads a sma...
Stanford researchers have released Memorilla, an Apache 2.0 open-source latent memory system for frozen LLMs. A 194M-parameter trainable module reads a document collection and supplies a frozen Qwen3-8B decoder with 16 m...
Vercel Labs released UI SDK at 0.1.0-beta.1, an open-source headless library of 50+ UI behaviors that coding agents assemble into accessible components across React, Vue, Svelte, Solid and Web Components. It ships a core...
The No AI Slop manifesto was introduced by Dex in the closing keynote at AIE CODE after cosignatures from conference speakers and is published at slopmanifesto.com. It is intended as a discussion tool for teams, and the...
Researchers built a multi-sub-task coding setting to test whether LLMs encode goals as internal representations that guide action across different execution paths. They localized an encoding of the next sub-goal in the o...
Researchers introduced GeoWorld, a controllable geographic environment platform for LLM agents, and LiveGeo, a benchmark for evaluating reliable decision-making as real-world geographic states evolve. LiveGeo requires ag...