Agents & Tool Use A

Showing 1–30 of 51
  • ITmedia AI+ · JA Agents & Tool Use extract
    「AI、結局使えないじゃん」問題 セールスフォースが431万件対応で導いた正解
    Salesforce turns AI into ROI, handling 4.31M cases in-house
    AI Agents
    Salesforce completed 4.31 million customer interactions through its own 'customer zero' practice, lifting deal counts by 40-50%. COO Ryota Tanaka outlines the playbook—choosing domains with solid data and KPIs, and starting with simple, high-frequency tasks—to convert AI investment into clear returns.
    Read original (ITmedia AI+) ↗
  • ITmedia AI+ · JA Agents & Tool Use extract
    賞金1000万のAIコンテスト、でも「実現性は問わず」 サイバーエージェントのAI推進策
    CyberAgent's ¥10M AI contest ignores feasibility to shift staff mindset
    AI Agents
    CyberAgent ran an AI contest with a 10-million-yen prize that deliberately ignores feasibility, aiming to change how employees engage with generative AI. Since tools yield no value if unused, lowering the barrier to entry is meant to spur company-wide adoption.
    Read original (ITmedia AI+) ↗
  • Sakana AI Blog (ja) · JA New Model Releases extract
    Sakana AI、日本語特化のLLM API「Sakana Namazu」を提供開始
    Sakana AI launches Namazu, a Japanese-focused OpenAI-compatible LLM API
    AI Agents Inference Machine Learning Meta OpenAI
    Sakana AI released Namazu, an LLM API tuned for Japanese and local business use. Built on Moonshot AI's open Kimi K2.6 and refined with in-house data, it adds built-in web search and code execution. Being OpenAI-compatible, existing code works by swapping the base_url, filling the gap between costly frontier models and raw open ones.
    Read original (Sakana AI Blog (ja)) ↗
  • Simon Willison's Weblog · EN New Model Releases extract
    July 2026 newsletter
    Simon Willison publishes his latest monthly newsletter
    Anthropic Claude DeepSeek GPT Model Context Protocol (MCP)
    Developer Simon Willison released the latest edition of his sponsors-only monthly newsletter. It rounds up recent developments across AI models and tooling—spanning GPT, Claude, DeepSeek, Anthropic, and MCP—offering an individual's closely watched view of the fast-moving AI landscape.
    Read original (Simon Willison's Weblog) ↗
  • ITmedia AI+ · JA New Model Releases extract
    Google、パーソナルAI「Gemini Spark」を日本でも利用可能に Chrome統合は米国から
    Google expands Gemini Spark personal AI to 160+ countries incl. Japan
    AI Agents Gemini Google
    Google extended its Gemini Spark personal AI agent to more than 160 countries, including Japan. Running on Google's cloud, it can act even when a PC is off or a phone is locked, handling tasks based on triggers. Chrome integration will roll out first in the US.
    Read original (ITmedia AI+) ↗
  • Simon Willison's Weblog · EN New Model Releases extract
    Stateless MCP has recaptured my interest (and inspired mcp-explorer and datasette-mcp)
    Simon Willison: stateless MCP (MCP 2.0) has recaptured my interest
    Anthropic Claude Model Context Protocol (MCP) OpenAI Reinforcement Learning
    Simon Willison wrote that the rollout of stateless MCP—the MCP 2.0 or 2026-07-28 Model Context Protocol specification—has renewed his interest in the protocol. He says it inspired him to build tools such as mcp-explorer and datasette-mcp on top of the new stateless design.
    Read original (Simon Willison's Weblog) ↗
  • Simon Willison's Weblog · EN New Model Releases extract
    llm-mcp-client 0.1a0
    Simon Willison releases llm-mcp-client 0.1a0
    Model Context Protocol (MCP)
    Simon Willison released llm-mcp-client 0.1a0, a tool for connecting his LLM utility to Model Context Protocol (MCP) servers. Detailed in an accompanying blog post, the release adds to the growing set of tooling built around the MCP ecosystem.
    Read original (Simon Willison's Weblog) ↗
  • Simon Willison's Weblog · EN New Model Releases extract
    datasette-agent 0.4a0
    Datasette Agent 0.4a0 lets agent tools run code in the user's browser
    Datasette Agent 0.4a0 adds an await context.browser_task() mechanism that lets agent tools execute custom JavaScript directly in the user's browser. The release makes it easier for Datasette Agent plugins to provide tools that run client-side.
    Read original (Simon Willison's Weblog) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN Infrastructure & Hardware
    Beyond Component Testing: Validating Agentic AI Systems
    Neural Network Retrieval-Augmented Generation (RAG)
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN Agents & Tool Use
    Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents
    AI Agents Deep Learning Inference Retrieval-Augmented Generation (RAG) Reinforcement Learning
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • arXiv cs.CL (Computation and Language) · EN Agents & Tool Use
    Data Turnstile: A Scalable Open Framework for Function-Calling Data Generation
    Neural Network
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN Safety & Evaluation
    Don't Mix Rewards, Mix Policies: Policy Decomposition and Optimization for Multi-Reward RL
    Inference Reinforcement Learning Software Engineering
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • ITmedia AI+ · JA Developer Tools extract
    PerplexityがAIエージェントの“暴走”対策ツールをオープンソースに Claude CodeやCodexを監視
    Perplexity open-sources 'Numbat' to rein in runaway AI agents
    AI Agents Claude
    Perplexity open-sourced Numbat, a set of tools to detect and prevent dangerous AI agent behavior. Integrated with Claude Code and Codex, it aims to stop task-obsessed agents from going rogue before actions execute, adding a safeguard for autonomous agent workflows.
    Read original (ITmedia AI+) ↗
  • ITmedia AI+ · JA Inference & Efficiency extract
    Chromeに13年以上潜んでいた脆弱性、AIで発見 直近2回のアプデで過去23回分を上回るバグ修正
    Google's Gemini agent finds 13-year-old Chrome flaw; tests twice-weekly updates
    AI Agents Gemini Google
    Google detailed its use of AI for Chrome security, saying a Gemini-based agent uncovered a vulnerability hidden for over 13 years and that its last two updates fixed more bugs than the previous 23 combined. To counter faster AI-driven attacks, Google is trialing twice-weekly security updates.
    Read original (ITmedia AI+) ↗
  • NVIDIA Developer Blog · EN Agents & Tool Use extract
    Four Ways to Deploy More Secure AI Agents
    NVIDIA outlines four ways to deploy more secure AI agents
    AI Agents Generative AI NVIDIA
    NVIDIA outlined four approaches to deploying AI agents more securely in production, covering access controls, guardrails, and monitoring. The guidance targets security risks that arise as autonomous agents take on real workloads.
    Read original (NVIDIA Developer Blog) ↗
  • arXiv cs.CL (Computation and Language) · EN Agents & Tool Use
    Benchmarks Are Not Validation: A System-Level View of Financial LLM Applications
    Generative AI Reinforcement Learning
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN Agents & Tool Use
    AskChem: Claim-Centered Infrastructure for Chemistry Literature Synthesis
    AI Agents GPT Model Context Protocol (MCP) Software Engineering
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • Publickey · JA New Model Releases extract
    JetBrains、AIが少ないトークンでコンテキストを取得しやすく、よりよいコード生成を可能にする「JetBrains Context」発表
    JetBrains unveils 'JetBrains Context' to feed AI agents code context efficiently
    AI Agents Machine Learning
    JetBrains announced JetBrains Context, a service that builds an intelligence layer over code repositories. By supplying AI agents with the right code context using fewer tokens, it aims to enable better code generation from agentic coding tools.
    Read original (Publickey) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN New Model Releases
    MANTA: Multi-Agent Network Topology Adaptation for Self-Evolving Multi-Agent Systems
    Inference Neural Network Retrieval-Augmented Generation (RAG)
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • Microsoft Research Blog · EN Agents & Tool Use extract
    Echoverse: Deep, evolving environments for computer-use agents
    Microsoft's Echoverse trains computer-use agents in evolving environments
    AI Agents Microsoft
    Microsoft Research unveiled Echoverse, a set of deep, evolving environments for training computer-use agents that struggle with multi-step workflows such as email and customer support. Training in realistic settings aims to improve agents' ability to complete complex tasks.
    Read original (Microsoft Research Blog) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN New Model Releases
    EMBL AI Librarian: Life-Sciences Knowledge Layer for AI Agents
    AI Agents GPT Software Engineering
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • arXiv cs.LG (Machine Learning) · EN Agents & Tool Use
    ClawTrack: Towards Trace-Level Evaluation and Improvement of Real-World Autonomous Agents
    AI Agents Reinforcement Learning
    Read original (arXiv cs.LG (Machine Learning)) ↗
  • arXiv cs.CL (Computation and Language) · EN Training & Fine-tuning
    FinanceHarness: Autonomous Financial Deep Research Framework
    AI Agents
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN Agents & Tool Use
    Can AI agents conduct open-ended AI research? Early evidence from two case studies
    AI Agents Reinforcement Learning Software Engineering
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN New Model Releases
    Partner Capability Estimation for Task-Agnostic Adaptation in Ad-Hoc Teamwork
    AI Agents Deep Learning Neural Network
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • NVIDIA Developer Blog · EN Agents & Tool Use extract
    How to Self-Host a Validated AI Coding Assistant with NVIDIA NeMo Guardrails
    NVIDIA: self-host a validated AI coding assistant via NeMo Guardrails
    AI Agents Generative AI NVIDIA
    An NVIDIA developer-blog post on self-hosting a validated AI coding assistant using NeMo Guardrails, framed around agent operation, infrastructure and safety. Note: the raw excerpt was blocked by a content guard, so specific components, supported models and guardrail rules are inferred from the title and URL and remain unverified from the body.
    Read original (NVIDIA Developer Blog) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN Agents & Tool Use
    Scores Are Not Decisions: Cost-Aware Stopping for Tool Acquisition in LLM Agents
    AI Agents Neural Network
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • Sakana AI Blog (ja) · JA New Model Releases extract
    Sakana AI防衛・インテリジェンスチーム、「DIVER OSINT CTF 2026」で5位入賞 Fuguを活用したOSINTエージェントの可能性
    Sakana AI's defense team places 5th at DIVER OSINT CTF 2026
    AI Agents
    Sakana AI's defense and intelligence team placed fifth at the DIVER OSINT CTF 2026 competition, using its Fugu tool to power an OSINT agent. The result highlights the potential of AI agents for open-source intelligence and information-analysis tasks.
    Read original (Sakana AI Blog (ja)) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN Agents & Tool Use
    What Does It Take to Detect an AI Agent? Minimal Feature Sets for Behavioral Detection under Browser Automation
    AI Agents Machine Learning Neural Network Transformer
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN Agents & Tool Use
    SecRespond: Benchmarking AI Agents for Real-World Post-Compromise Incident Response
    AI Agents Neural Network Reinforcement Learning
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗