←Search results

Search “Agents”

By relevance · Total 6789 results Clear search

Wednesday

  2. Arena

    Meta Muse Wonder Full (Max) rises to #7 in Agent Arena

    Meta's Muse Wonder Full (Max) ranks #7 in Agent Arena with a net gain of +11.3%, covering over 6.5K real agent sessions and helping Meta rise to #4 among labs. The model is 7.5 percentage points higher than Muse Wonder (Max) and 7.8 percentage points higher than Muse Spark 1.3 (Max), with category rankings of #5 in Chat, #6 in Code, and #7 in Work. At the signal level, it ranks #6 in Praise vs. Complaint (+21.9%), #6 in Confirmed Success (+13.4%), #7 in Steerability (+11.2%), and #16 in Bash Reliability (+7.7%), with no issues in Tool Hallucination.

    Meta's Muse Wonder Full (Max) ranks 7 in Agent Arena with a net gain of +11.3%, covering over 6.5K real agent sessions and helping Meta rise to 4 among labs. The model is 7.5 percentage points higher than Muse Wonder (Max) and 7.8 percentage points higher than Muse Spark 1.3 (Max), with category rankings of 5 in Chat, 6 in Code, and 7 in Work. At the signal level, it ranks 6 in Praise vs. Complaint (+21.9%), 6 in Confirmed Success (+13.4%), 7 in Steerability (+11.2%), and 16 in Bash Reliability

    Matched fieldsTitle、Summary、Body

    #editorial#Evaluations / benchmarks#Agents#Meta
  4. AWS Machine Learning

    From Data to Decisions: Building Conversational Supply Chain Intelligence with Amazon Quick and Amazon Bedrock AgentCore

    The combination of Amazon Quick and Amazon Bedrock AgentCore turns supply chain data from systems such as ERP, monitoring, and procurement into a conversational MCP tool layer, so users can get cross-system answers in natural language. In the example, a TechComp production stoppage event is assessed via assess_disruption_impact, which finds a $750K risk, 23 orders, and three days of inventory, and recommend_mitigation then chains together governance and quoting tools to generate an emergency RFQ. All changes require approval from designated personnel, and the same workflow can also be triggered to run automatically on a schedule or by email.

    Diagram showing domain expertise with business users while operational data is split across ERP, monitoring, procurement, and email systems

    The combination of Amazon Quick and Amazon Bedrock AgentCore turns supply chain data from systems such as ERP, monitoring, and procurement into a conversational MCP tool layer, so users can get cross-system answers in natural language. In the example, a TechComp production stoppage event is assessed via assess disruption impact, which finds a $750K risk, 23 orders, and three days of inventory, and recommend mitigation then chains together governance and quoting tools to generate an emergency RFQ

    Matched fieldsTitle、Summary、Body

    #lab#Tutorials / practice#Agents#English text is being prepared.
  5. AWS Machine Learning

    AWS Publishes Agent Registry Runtime Tool Discovery Practice

    AWS introduces the Agent Registry runtime tool discovery approach: agents use hybrid semantic and keyword search to find approved MCP servers and A2A agents, then instantly build clients from descriptors to execute requests. The sample code is based on Amazon Bedrock AgentCore Gateway and runtime, integrates an order management MCP server and two A2A agents for pricing and customer service, and demonstrates a return and refund scenario using pure semantic matching. The registry returns only connection metadata; invocation credentials must be obtained separately through Cognito OAuth or IAM, and new capabilities require no changes to orchestrator code.

    Comparison of hardcoded tool endpoints versus runtime discovery with AWS Agent Registry

    AWS introduces the Agent Registry runtime tool discovery approach: agents use hybrid semantic and keyword search to find approved MCP servers and A2A agents, then instantly build clients from descriptors to execute requests. The sample code is based on Amazon Bedrock AgentCore Gateway and runtime, integrates an order management MCP server and two A2A agents for pricing and customer service, and demonstrates a return and refund scenario using pure semantic matching. The registry returns only conn

    Matched fieldsTitle、Summary、Body

    #lab#Tutorials / practice#Agents#English text is being prepared.

Tuesday

  1. ElevenLabs Blog

    Trinity Logistics automates inbound calls with ElevenAgents, boosting profit margin by 25%

    Trinity Logistics moved its inbound sales process to ElevenLabs' ElevenAgents, automating carrier quote requests, negotiation, and booking. Automated freight profit margins are 25% higher than with the old system, and platform costs per minute are 40% lower. The system handles about 30,000 inbound calls per month, automatically books 1,000 freight loads, matches the old system's 4% successful booking rate, and handles about 60% to 70% of carrier calls.

    Jessica Day Headshot

    Matched fieldsTitle、Summary、Body

    #company#Industry news#Speech#Agents
  4. Philipp Schmid

    Gemini Managed Agents supports running Gemini 4 Argon agents with a single API call

    Philipp Schmid explains that the easiest way to try Gemini 4 Argon in an agent environment is Gemini Managed Agents, where a single API call provides Python, Node.js, Git, and Bash, along with full network access and control, a dedicated Credentials API, a file system for persistent work, and background support. The tweet includes a link.

    Matched fieldsTitle、Summary、Body

    #editorial#Product updates#Agents#English text is being prepared.
  10. Rohan Paul

    The Qwen3.8-27B reinforcement-learning post-trained model surpasses GPT-6 Luna high on multiple Agent benchmarks

    Rohan Paul introduced an open-source environment model built on Qwen3.8-27B with reinforcement-learning post-training, which reduced the hallucination rate on AA-Omniscience from 30.4% to 15.1%. The model surpasses Muse Glimmer 30B and GPT-6 Luna high on Terminal-Bench, τ³-bench, ClawEval, and BFCL v4, but Luna still leads on DeepSWE at 53.1%; its median output for solved tasks is 23.8K tokens, compared with 54.9K for base Qwen. The author also mentions that the MLA version replaces 16 layers of full attention with multi-head latent attention, reducing memory usage per token from 64 KiB to 18 KiB; the compressed version can run on a single 24 GB RTX 4090, with a context about 3.5 times that of base Qwen.

    Rohan Paul introduced an open-source environment model built on Qwen3.8-27B with reinforcement-learning post-training, which reduced the hallucination rate on AA-Omniscience from 30.4% to 15.1%. The model surpasses Muse Glimmer 30B and GPT-6 Luna high on Terminal-Bench, τ³-bench, ClawEval, and BFCL v4, but Luna still leads on DeepSWE at 53.1%; its median output for solved tasks is 23.8K tokens, compared with 54.9K for base Qwen. The author also mentions that the MLA version replaces 16 layers of

    Matched fieldsTitle

    #ai-news#Model releases#Open-source ecosystem#Reasoning
  12. 36Kr · AI

    MiniMax Releases M3.1 Flash, Scoring 29.6% on Agents' Last Exam to Rank First Among Chinese Models

    MiniMax has officially released M3.1 Flash, the model previously known as Space Bunny (Yutu) that topped the charts anonymously on OpenRouter. It scores 29.6% on Agents' Last Exam, ranking first among Chinese models. The model achieves 73.7% on DeepSWE v1.1, 82.2 points on CyberGym, and 61.7 points on OSWorld V2, with output speeds of up to 200+ TPS and a P50 maintained at 170+ TPS. Pricing is 1 yuan per million input tokens, 4 yuan for output, and 0.1 yuan for cache reads.

    Matched fieldsTitle、Summary、Body

    #hot-signal#Model releases#Agents#English text is being prepared.