AgentCore-8B
A model post-trained for tool use and multi-step planning.
Papers115
This paper describes the participation of HULAT2-UC3M in the Spanish track of MER-TRANS 2026, a shared task on multiling
paperTraceLab: Characterizing Coding Agent Workloads for LLM ServingCoding agents are rapidly becoming a major application of agentic LLMs, but serving them efficiently remains challenging
paperTrustX Agent Risk Classification Framework (ARC): Risk-Tiering Internally Created Agentic AI SystemsThe proliferation of agentic AI systems across enterprise and public-sector contexts has outpaced the capacity of genera
paperWhen Local Monitors Miss Compositional Harm: Diagnosing Distributed Backdoors in Multi-Agent SystemsAs multi-agent, tool-using LLM systems are deployed, a common safety net is a runtime monitor that checks each message,
paperMAGiSt3R: Multi-Agent Feed-forward 3D Reconstruction from Monocular RGB VideosThis paper presents MAGiSt3R, a multi-agent 3D reconstruction framework performing reconstruction and camera tracking fo
paperCortex: A Bidirectionally Aligned Embodied Agent Framework for Long-horizon ManipulationWhile recent Vision-Language-Action (VLA) models show promise toward generalist manipulation policies, they struggle wit
paperSAGEAgent: A Self-Evolving Agent for Cost-Aware Modality Acquisition in Multimodal Survival PredictionDoes every cancer patient truly need a complete diagnostic workup for accurate survival prediction? In multimodal clinic
paperToward Continuous Assurance for the Democratization of AI Agent Creation in IndustryAI agents are increasingly created inside organizations by non-engineering users through low-code, no-code, and conversa
Repos52
dashAI: an interactive platform for training, evaluating and deploying AI models
repoggwhite/4xAgentic AI development loop that splits Design, Code, Review, and Test into isolated roles with deterministic guardrails
repoCoplayDev/unity-mcpUnity MCP acts as a bridge between AI assistants and your Unity Editor. Give your LLM tools to manage assets, control sc
repotrpc-group/trpc-agent-goA Go framework for building production agent systems with graph workflows, tools, memory, A2A, AG-UI, MCP, evaluation, a
repoagenthatch/agenthatchTurn any skill into a standalone, runnable RAG-native AI Agent
repoSWE-agent/SWE-agentSWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for o
repoBoundaryML/bamlThe programming language for agents
repogeneralaction/emdashEmdash is the Open-Source Agentic Development Environment (🧡 YC W26). Run multiple coding agents in parallel. Use any p
News13
<!-- SC_OFF --><div class="md"><p>I worked on this project (<a href="https://github.com/workofart/harness-training">http
newsLearning to lead in a hybrid human-AI enterpriseAs adoption of AI agents looks set to surge by as much as 300% in the next two years, leadership teams are carefully con
newsAmazon Bedrock AgentCore harness is now generally available: Go from idea to production-grade agent in minutesToday, Amazon Bedrock AgentCore harness is generally available. Two API calls (CreateHarness to define an agent, and Inv
newsOrnith-1.0: self-improving open-source models for agentic coding<p>Article URL: <a href="https://github.com/deepreinforce-ai/Ornith-1">https://github.com/deepreinforce-ai/Ornith-1</a><
newsAI coding agents taught robots how to install GPUs and cut zip tiesNvidia's self-improvement program for robots enlists teams of AI coding agents.
newsOpen-source agent framework crosses 50k starsThe toolkit for building tool-using agents sees rapid community adoption.
newsBuild generative UI for AI agents on Amazon Bedrock AgentCore with the AG-UI protocolThis post walks through how AG-UI integrates into the Fullstack AgentCore Solution Template (FAST) to build interactive
newsMost AI agents have no concept of opportunity cost [D]<!-- SC_OFF --><div class="md"><p>One thing that's been bugging me is how casually a lot of agents use tools. </p> <p>Ev