←Search results

Search “Agents”

By relevance · Total 6704 results Clear search

Tuesday

  2. 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
  4. 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.
  9. Cursor BlogSelected

    Cursor Releases Agent SDK, Enabling Code-Defined Agents with One-Click Deployment

    Cursor has released the Agent SDK, the framework it uses to build hosted agents such as Bugbot, Security Reviewer, and Rollouts. Developers can define agents in code and deploy them to Cursor infrastructure with a single command, agent-sdk deploy. Agents are organized as small software projects, with prompts written in Markdown and tools defined as TypeScript functions. They can respond to PR events from GitHub, GitLab, and Bitbucket, and include built-in evals and event replay. They can also be packaged to run as a single Node process on your own infrastructure.

    Cursor has released the Agent SDK, the framework it uses to build hosted agents such as Bugbot, Security Reviewer, and Rollouts. Developers can define agents in code and deploy them to Cursor infrastructure with a single command, agent-sdk deploy. Agents are organized as small software projects, with prompts written in Markdown and tools defined as TypeScript functions. They can respond to PR events from GitHub, GitLab, and Bitbucket, and include built-in evals and event replay. They can also be

    Matched fieldsTitle、Summary、Body

    #company#Product updates#Agents#English text is being prepared.
  12. Shao Meng

    MIT Course MAS.S62: Two Lectures on the Evolution of Harnesses and Multi-Agent Systems

    Lectures 4-5 of the MIT course MAS.S62 "How to AI an AI" focus on Harness evolution, covering the evolution of harness components, memory, tools, and skills, as well as the evolution of planning, task decomposition, and multi-agent systems. The memory section uses a three-axis taxonomy to connect MemGPT, mem0, MEM1, and Reflexion/ExpeL, and uses CLM to unify context management as file operations; the tools section moves from Toolformer, ToolLLM, and CodeAct to Meta-Harness, which represents the entire harness as a file system and provides about 400 times the amount of feedback information of previous methods. The multi-agent section presents five empirical findings, including that MAS wins 81% on decomposable tasks and loses 70% on tasks with sequential dependencies, and that CORAL achieves new SOTA on 8 tasks, with multi-agent evolution improving over single-agent by 4%-20%.

    AI an AI" focus on Harness evolution, covering the evolution of harness components, memory, tools, and skills, as well as the evolution of planning, task decomposition, and multi-agent systems. The memory section uses a three-axis taxonomy to connect MemGPT, mem0, MEM1, and Reflexion/ExpeL, and uses CLM to unify context management as file operations; the tools section moves from Toolformer, ToolLLM, and CodeAct to Meta-Harness, which represents the entire harness as a file system and provides a

    Matched fieldsTitle、Summary、Body

    #hot-signal#Tutorials / practice#Agents#English text is being prepared.
  16. Rohan Paul

    AgentCloak founder's Mac Mini smashing video gets 2.2 million views

    AgentCloak founder Peter Yared smashed a Mac Mini on camera, and the launch video got 2.2 million views and 3,000 downloads. launchvideo.com ran the launch like an assembly line: a founder on-camera video, with creators rolling it out in batches by audience size. The team had also shot an alternate ending featuring a $10,000 Mac Studio setup and a closing laptop, but ultimately kept the smashing as the main shot, and the alternate version was not used.

    Matched fieldsTitle、Summary、Body

    #ai-news#Industry news
  18. ArenaSelected

    DeepSeek-V4.1-Flash-20261017 Tops the Agent Arena Open-Model Leaderboard

    Arena.ai says DeepSeek-V4.1-Flash-20261017 (Max) has become the top-ranked open-source model in Agent Arena, ranking 11th overall, with a net improvement of 5.1% across more than 7.5K real sessions. The model's median cost per task is $0.20, roughly 37% of GPT-6.1 Sol's improvement margin and 27% of its cost; it ranks first among open-source models on all four signals—Confirmed Success, Praise vs. Complaint, Bash Reliability, and Steerability—and shows no tool-hallucination issues.

    Matched fieldsTitle、Summary、Body

    #editorial#Evaluations / benchmarks#Agents#DeepSeek

Wednesday

  1. 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.

Monday