Latest Articles

• Abstract-CoT: Reasoning Tokens Slashed 11.6x, Chain-of-Thought Without Words Shatters LLM Efficiency Ceiling
  Artificial IntelligenceLarge Language ModelsResearchMachine LearningNatural Language Processing

  ...
• Paper Brief | Automated Knowledge Graph Enrichment Using Multi-Agent Large Language Models (NeurIPS 2025)
  Artificial IntelligenceKnowledge GraphsMachine LearningScientific ComputingNatural Language Processing

  ...
• DeepMind's Nobel-winning CEO's latest interview: The current large model path is not a dead end, but the brute-force methods everyone uses might be wrong; Chinese models are already leading in the open-source domain
  Artificial IntelligenceAGIMachine LearningDeepMindOpen Source AI

  ...
• code-review-graph: The Tool That Makes AI Code Reviews Read Only the 'Key Code'
  TechnologyProgrammingArtificial IntelligenceOpen Source

  ...
• An Excellent New Systematic Survey of Self-Evolving Agents
  Artificial IntelligenceLLM AgentsMachine LearningSurveySelf-Evolution

  ...
• Claude 4.6 Only Scores 66%? Claw-Eval-Live Says: Fixing a Terminal ≠ Cross-System Capability
  Artificial IntelligenceAI AgentsTechnologyModel EvaluationBenchmarking

  ...
• Your Agent Isn't Really Learning—It's Just Flipping Through a Notebook
  Artificial IntelligenceAgent MemoryLarge Language ModelsAI SafetyMachine Learning Theory

  ...
• AI Is Pushing Us Into a 'Lose-Lose' Abyss: Top Paper Reveals the 'AI Layoff Trap'
  Artificial IntelligenceEconomicsTechnology PolicyAutomationLabor Market

  ...
• What Did DeepSeek's Overnight Deleted New Paper Actually Say?
  TechnologyArtificial IntelligenceComputer VisionDeep Learning

  ...
• The Era of Software 3.0 Has Arrived
  Artificial IntelligenceSoftware DevelopmentAgentic AITech Industry TrendsLarge Language Models

  ...
• Qwen-Scope: Seeing Through the 'Hidden Thoughts' of Large Models
  AI InterpretabilitySparse AutoencoderData SynthesisModel OptimizationLarge Language Models

  ...
• Next-Gen AI Terminal Tool Goes Open Source, Skyrocketing to 46K Stars!
  TechnologyOpen SourceDeveloper ToolsSoftware DevelopmentArtificial Intelligence

  ...
• The Father of GPT Throws AI Back to 1930: Never Saw a Line of Code, Yet 'Invented' Python!
  Artificial IntelligenceLarge Language ModelsMachine LearningGPTHistorical AI

  ...
• Is RAG Dead? No, Grep is Making a Comeback!
  AI Coding ToolsSoftware DevelopmentDeveloper WorkflowsToken OptimizationCodebase RetrievalTechnology IndustryCode GenerationSearch Technology

  ...
• Scaling Pain: Lessons from Serving Ultra-Large-Scale Coding Agents
  AI InfrastructureLarge Language ModelsCoding AgentsSystems EngineeringInference Optimization

  ...
• ChatGPT's Math Evolution! OpenAI Researchers Reveal: From Miscounting to Solving Erdős Problems with Novel Methods; Math as a Key Benchmark for Model Progress; The AI Automated Researcher
  Artificial IntelligenceMathematicsTechnologyResearchOpenAI

  ...
• Anthropic's Project Glasswing: Mythos Crushes Opus 4.6, National Security Becomes a Fig Leaf for the Collusion of Tech Giants and Intelligence Agencies
  AI CybersecurityZero-Day VulnerabilityTech PolicyNational SecurityAI Ethics

  ...
• Anthropic's Latest Blog: MCP Isn't Dead, We Revived It
  AI & Machine LearningModel Context ProtocolCloud ComputingDeveloper ToolsAgent Architecture

  ...
• Symphony: Every Issue Gets Its Own Agent, Humans Just Review the Results
  TechnologyArtificial IntelligenceAutomationOpen SourceSoftware Development

  ...
• Skills-Driven Reasoning Paradigm: Tsinghua & Peking University Propose TRS, Saving 59% Tokens Without Accuracy Drop
  Artificial IntelligenceLarge Language ModelsReasoning SystemsEfficiency OptimizationMachine Learning

  ...