#Agent

Perplexity has launched the 'AI Companion' feature on its Mac app, creating all-weather digital employees.

Perplexity releases Mac version app update, Max subscribers can now experience AI smart body function 'Teammates', previously only supported on iOS and web.

Hugging Face releases XYBench benchmark to evaluate AI assistants' ability to solve problems based on misunderstandings

Hugging Face releases XYBench benchmark, containing 8150 real-world problems, to evaluate AI assistants' ability to identify user misunderstandings and guide them to correct solutions. Claude Sonnet 4.6, GPT-5, Gemini 3.1 Pro, Qwen3.5-9B, and DeepSeek-V4 Pro tend to focus on user errors (Y) rather than actual goals (X), with only 35-41% of responses centered on the actual goals.

LangChain completed a $300 million Series C funding, valuing the company at $3 billion.

Claude Duet Agent: Both Anxious and Unexpectedly Helpful

Anthropic's Claude Duet is an AI assistant aimed at consumers, designed to help non-programmer users manage their tasks. The assistant connects to services like users' email, calendars, Google Docs, and Slack, offering features such as daily summaries, to-do suggestions, and message drafting.

openJiuwen releases RSI native AgentOS, allowing Agents to transform freely and iterate continuously

openJiuwen has launched RSI Native AgentOS, which enables Agent self-improvement and functional iteration through extensions, supporting customized modifications to the interface, gateway, server, and Agent behavior. WorkSwarm applications can dynamically load system plugins to enhance functionality.

How does Claude achieve self-evolution?

An evolutionary intelligent agent can change the way future tasks are handled through experience, with its improvements primarily occurring in the harness around the model, such as instructions, context, tools, and software. Evaluating the improvement effect requires checking whether the agent uses correct information, takes correct actions, and meets user needs, such as verifying budget and dietary requirements in a restaurant planning task. The agent can autonomously review tasks, identify repetitive errors, propose improvement solutions, and test their effectiveness, but it requires setting the range of modifiable harness modules, such as context management, agent loops, and tool usage.

MIT researchers develop an AI collaboration design system to help engineers optimize structures

MIT Researchers Develop AI Collaboration Design System, Providing Feedback Areas to Human Designers When Algorithms Generate Structures, Making Structures Easier to Manufacture and More Bending-Resistant, with Only a 15-Second Increase in Total Design Time. The System is Based on Topology Optimization Technology, Rapidly Identifying Algorithm Design Areas Humans May Want to Modify Through Machine Learning, Integrating Human Knowledge into the Design Process, Increasing Manufacturability and Linear Bending Load by 39% While Only Moderately Increasing Total Design Time.

GitHub Blog: Build Once, Run Across Any Agent: A Practical Guide to Agent Skills

Agent skills allow the capture of reusable instructions for users and agents, defining the timing and manner of task execution through a versioned directory centered around a SKILL.md file. Proof Agent uses an independent validator for adversarial validation of AI-generated content, while Data Forge constructs a support pipeline for table metrics through multiple collaborative skills, with each skill sharing context defined by a manifest rather than independently rediscovering it.

How Natera uses Amazon Bedrock AgentCore to design intelligent agent systems to optimize laboratory operations

Natera developed the SWARM intelligent agent system to address knowledge gaps caused by laboratory equipment failures, achieving 130x response speedup and 96.2% automation support for handling work orders through Amazon Bedrock AgentCore.

Nectar launches AI agent automation brand creator discovery and connection

Nectar launches 'Creator Intelligence' that can search over 300 million creators, analyze content and brand collaborations, automatically send personalized messages and manage collaborations, supporting Instagram creators and TikTokers, available globally and plans to integrate other AI assistants like Claude, ChatGPT, Copilot through Model Context Protocol (MCP).

Why Git needs help: From file to system for source code control

Anthropic will struggle with traditional Git infrastructure by the end of 2026 when autonomous agent activities cause daily merge volumes per repository to exceed 30,000. Claude Sonnet 4.6 replaces string diffs of 2,000+ lines with AST node transformations, reducing the cost of modifying each file to O(node_delta) and enabling subsecond dependency analysis, but standard Git still discards reasoning history such as agent execution logs and compilation feedback.

Galaxy Smart Learning's Little Deer Love Learning introduces a dual-core technology architecture to support scalable personalized instruction.

Galaxy Smart Learning has launched an AI education product, Xiao Lu Ai Xue, which adopts a dual-core architecture of the Doubao large model and a self-researched intelligent learning engine. It achieves learning situation diagnosis by analyzing students' answer records and develops functions such as learning situation diagnosis, ability assessment, learning difficulty matching, and task planning. The student-side intelligent agent recommends learning tasks and explains the basis, while the teacher-side intelligent agent summarizes student performance for personalized guidance reference. The product has served over 500 schools, covering 24 provinces, and supports teachers in adjusting teaching strategies through a human-machine co-education model.

How does OpenRouter Agent SDK prevent AI agents from falling into infinite loops?

The OpenRouter Agent SDK, by enabling doom-loop detection, prevents infinite loops in six tested models when the third identical tool call is received; combining stepCountIs(40) and maxCost(x) can limit the number of runs and cost; the credit limit of the API key can control total expenditure, these measures effectively reduce the number of tool calls (from 314 to 64) and costs (from $0.29 to $0.05).

Evaluating Evaluators: Investigating the Performance of LLM Judges in Personalized Writing Style Evaluation

Researchers evaluated the performance of Large Language Model (LLM) judges in personalized writing tasks and found that the quality of judges is weakly correlated with general LLM capabilities measured by MMLU (Pearson’s ρ ≤ 0.2), and their performance is influenced by writing tasks and evaluation criteria (e.g., general helpfulness vs. stylistic personalization). LLM evaluators were more consistent and performed better in pairwise comparisons than in independent scoring responses. The 'strongest' LLM did not reliably replicate human evaluations, possibly due to being overly sensitive to subtle details overlooked by human annotators and weaker LLMs.

Google launches Gemini Decisions API and Gemini Decision 1 model

Google releases generative UI open protocol A2UI 1.0

Google has released the Generative UI Open Protocol A2UI 1.0, which is the first stable version of the protocol, allowing AI agents to respond with interactive interfaces instead of plain text. Version 1.0 adds bidirectional function calls, accessibility support, and extended metadata, and provides open-source rendering SDKs for Web, Android, iOS, as well as agent SDKs for Python, TypeScript, and Dart.

Databricks upgrades Genie One to an enterprise AI collaboration workspace

Databricks announces Genie One as the unified entry point for enterprise AI collaboration, consolidating search, product generation, and cross-tool operations into one place, and providing enterprise context based on Genie Ontology, governed by Unity Gateway.