Impact Library(影响力文章与论文)
规则:按发布时间顺序(旧 → 新);每条给出影响力评分(1-10)。
- 2025-12-01 | 示例论文 A | 影响力 8.7/10
- 2026-01-06 | From Augmentation to Symbiosis: A Review of Human-AI Collaboration Frameworks | 影响力 9.1/10
- 2026-01-15 | 示例文章 B | 影响力 8.2/10
- 2026-02-17 | GitHub previews Agentic Workflows as part of continuous AI concept | 影响力 8.4/10
- 2026-02-19 | EvoMap Protocol Released: AI Agents Can Achieve Experience Sharing and Autonomous Evolution via "Gene Capsules" | 影响力 8.7/10
- 2026-02-20 | Moltbook, the 'thriving' social network for AI agents, is just a small echo chamber researchers hijacked in days | 影响力 8.7/10
- 2026-02-21 | OpenClaw AI Agents as Informal Learners at Moltbook: Characterizing an Emergent Learning Community at Scale | 影响力 9.0/10
- 2026-02-21 | OpenClaw 榜一外掛被下架後,他用兩周做了一套協議,想讓 Agent 自己進化 | 影响力 8.4/10
- 2026-02-21 | Moltbook and the Illusion of “Harmless” AI-Agent Communities | 影响力 8.8/10
- 2026-02-22 | Let There Be Claws: An Early Social Network Analysis of AI Agents on Moltbook | 影响力 9.3/10
- 2026-02-22 | Galaxy AI Expands Multi-Agent Ecosystem To Give Users More Choice and Flexibility | 影响力 8.6/10
- 2026-02-22 | Designing Effective Multi-Agent Architectures | 影响力 8.6/10
- 2026-02-23 | OpenClaw, Moltbook, and ClawdLab: From Agent-Only Social Networks to Autonomous Scientific Research | 影响力 8.7/10
- 2026-02-23 | AI agents have their own social network: Moltbook study tracks topics and toxicity | 影响力 9.0/10
- 2026-02-24 | The 2025 AI Agent Index: Documenting Technical and Safety Features of Deployed Agentic AI Systems | 影响力 8.9/10
- 2026-02-24 | Multi-agent workflows often fail. Here’s how to engineer ones that don’t. | 影响力 8.7/10
- 2026-02-24 | Anthropic launches new push for enterprise agents with plug-ins for finance, engineering, and design | 影响力 8.7/10
- 2026-02-24 | New Relic launches new AI agent platform and OpenTelemetry tools | 影响力 8.5/10
- 2026-02-24 | Gas Town, OpenClaw and the rise of open source AI agents | 影响力 8.9/10
- 2026-02-24 | Atlassian Introduces Agents in Jira to Drive Human-AI Collaboration at Enterprise Scale | 影响力 8.9/10
- 2026-02-24 | Cursor announces major update to AI agents as coding tool battle heats up | 影响力 8.7/10
- 2026-02-24 | Agentic AI Foundation Welcomes 97 New Members As Demand for Open, Collaborative Agent Standardization Increases | 影响力 9.2/10
- 2026-02-24 | Microsoft accelerates telecom return on intelligence with a unified, trusted AI platform | 影响力 8.4/10
- 2026-02-24 | Agentic AI Foundation Welcomes 97 New Members As Demand for Open, Collaborative Agent Standardization Increases | 影响力 8.8/10
- 2026-02-25 | Nebius and Toloka to introduce integration to bring human experts-on-demand to AI agents | 影响力 8.9/10
- 2026-02-25 | EvoMap: The Global AI Agent Evolution Network & GEP Protocol | 影响力 8.5/10
- 2026-02-25 | From agent sprawl to seamless alignment: Introducing agents in Jira | 影响力 8.8/10
- 2026-02-25 | I'm a solo founder with AI agents instead of employees. My 'council' of AI agents saves me 20 hours a week. | 影响力 8.6/10
- 2026-02-25 | Perplexity Challenges OpenClaw With Managed AI Agent | 影响力 8.8/10
- 2026-02-25 | China’s Huawei joins US giants OpenAI, Google in AI standards alliance | 影响力 8.9/10
- 2026-02-26 | EvoX: Meta-Evolution for Automated Discovery | 影响力 8.6/10
- 2026-02-26 | 一文带你了解 EvoMap 到底是干啥的?【附赠内测邀请码】 | 影响力 8.2/10
- 2026-02-26 | Are You ‘Agentic’ Enough for the AI Era? | 影响力 8.8/10
- 2026-02-27 | Moltbook, the AI Agent Network, Heralds a Messy Future | 影响力 9.2/10
- 2026-02-27 | Perplexity’s new tool deploys teams of AI agents | 影响力 8.7/10
- 2026-02-27 | OpenClaw: all the news about the trending AI agent | 影响力 9.1/10
- 2026-02-28 | OpenClaw进化指南:阿里云+Windows本地部署+EvoMap自进化配置,让AI Agent学会自我成长 | 影响力 8.3/10
- 2026-02-28 | Moltbook: The conversation we should be having | 影响力 8.6/10
- 2026-02-28 | AI Predictions for 2026: A DevOps Engineer's Guide | 影响力 8.4/10
- 2026-02-28 | Surprise! The One Being Ripped Off by Your AI Agent Is You | 影响力 8.3/10
- 2026-03-01 | Perplexity announces "Computer," an AI agent that assigns work to other AI agents | 影响力 8.9/10
- 2026-03-01 | Codified Context: Infrastructure for AI Agents in a Complex Codebase | 影响力 8.6/10
- 2026-03-01 | Toward Expert Investment Teams: A Multi-Agent LLM System with Fine-Grained Trading Tasks | 影响力 8.5/10
- 2026-03-01 | MoltGraph: A Longitudinal Temporal Graph Dataset of Moltbook for Coordinated-Agent Detection | 影响力 8.7/10
- 2026-03-01 | Huawei to Announce the Open Source Project of A2A-T Software, Boosting the Application of Agent Communication Standards | 影响力 8.5/10
- 2026-03-01 | Jira’s latest update allows AI agents and humans to work side by side | 影响力 8.8/10
- 2026-03-01 | Moltbook's alleged AI civilization is just a massive void of bloated bot traffic | 影响力 8.9/10
- 2026-03-01 | Destroyed servers and DoS attacks: What can happen when OpenClaw AI agents interact | 影响力 9.1/10
- 2026-03-02 | A Hierarchical Multi-Agent System for Autonomous Discovery in Geoscientific Data Archives | 影响力 8.6/10
- 2026-03-02 | AI Governance Lessons from OpenClaw and Moltbook | 影响力 8.2/10
- 2026-03-02 | EvoMap 全解:让 OpenClaw 不停进化的秘密 | 影响力 7.8/10
- 2026-03-02 | Don't Run OpenClaw on Your Main Machine | 影响力 8.7/10
- 2026-03-02 | OpenClaw in the Wild: Mapping the Public Exposure of a Viral AI Assistant | 影响力 9.0/10
- 2026-03-02 | AI agents in 2026: 5 ways they can help | 影响力 8.1/10
- 2026-03-02 | Moltbook This Weekend | 影响力 7.9/10
- 2026-03-02 | Samsung Advances Galaxy AI and Its Connected Ecosystem at MWC 2026 | 影响力 8.4/10
- 2026-03-02 | "Vibe coding": how sites like Moltbook can disrupt the AI industry | 影响力 8.4/10
- 2026-03-03 | How to Model AI Agents as Personas?: Applying the Persona Ecosystem Playground to 41,300 Posts on Moltbook for Behavioral Insights | 影响力 8.8/10
- 2026-03-03 | Molt Dynamics: Emergent Social Phenomena in Autonomous AI Agent Populations | 影响力 9.1/10
- 2026-03-03 | The train has left the station: Agentic AI and the future of social science research | 影响力 8.9/10
- 2026-03-03 | Critical OpenClaw Vulnerability Exposes AI Agent Risks | 影响力 8.7/10
- 2026-03-03 | Automation Anywhere and EvolutIA Deliver Next-Generation AI Agents that Reason and Decide for Enterprises | 影响力 8.3/10
- 2026-03-03 | Formula 1 and Salesforce Deepen Partnership, Expanding Agentforce to Grow Fan Connection Worldwide | 影响力 8.8/10
- 2026-03-03 | On Moltbook | 影响力 8.9/10
- 2026-03-03 | Qualcomm CEO predicts 2026 will be the year of the AI agent | 影响力 8.7/10
- 2026-03-03 | Why enterprise AI agents could become the ultimate insider threat | 影响力 8.8/10
- 2026-03-04 | Moltbook (Wikipedia entry updated) | 影响力 8.0/10
- 2026-03-04 | Moltbook is the agent security wake-up call for engineering leaders | 影响力 8.8/10
- 2026-03-04 | State governments are starting to pursue agentic AI | 影响力 8.5/10
- 2026-03-04 | OpenAI's AI data agent, built by two engineers, now serves thousands of employees — and the company says anyone can replicate it | 影响力 9.1/10
- 2026-03-05 | Moltbook and the Illusion of AI Society | 影响力 8.2/10
- 2026-03-05 | Luma launches creative AI agents powered by its new Unified Intelligence models | 影响力 8.6/10
- 2026-03-05 | The first ‘AI societies’ are taking shape: how human-like are they? | 影响力 9.3/10
- 2026-03-06 | From Moltbot to Moltbook | 影响力 8.5/10
- 2026-03-06 | OpenClaw: Everything You Need to Know About This Viral Open-Source AI Agent | 影响力 8.5/10
- 2026-03-06 | AI agents could pose a risk to humanity. We must act to prevent that future | 影响力 8.8/10
- 2026-03-09 | What Do AI Agents Talk About? Emergent Communication Structure in the First AI-Only Social Network | 影响力 9.0/10
- 2026-03-09 | EvoScientist: Towards Multi-Agent Evolving AI Scientists for End-to-End Scientific Discovery | 影响力 8.9/10
- 2026-03-09 | Microsoft taps Anthropic for Copilot Cowork in push for AI agents | 影响力 9.1/10
- 2026-03-10 | Meta acquires Moltbook, the AI agent social network | 影响力 8.8/10
- 2026-03-10 | Meta acquired Moltbook, the AI agent social network that went viral because of fake posts | 影响力 8.9/10
- 2026-03-10 | Exclusive: Meta acquires Moltbook, the social network for AI agents | 影响力 9.2/10
- 2026-03-10 | Meta just bought the social network for AI bots everyone’s been talking about | 影响力 8.8/10
- 2026-03-10 | Meta acquires AI agent social network Moltbook | 影响力 9.4/10
- 2026-03-10 | Meta acquires AI agent social network Moltbook | 影响力 8.7/10
- 2026-03-11 | Meta’s Moltbook deal points to a future built around AI agents | 影响力 8.9/10
- 2026-03-11 | Moltbook: Instagram owner Meta buys 'social media network for AI' | 影响力 8.8/10
- 2026-03-11 | Why Did Meta Acquire Moltbook, the AI-Only Social Network? | 影响力 8.6/10
- 2026-03-12 | Increasing intelligence in AI agents can worsen collective outcomes | 影响力 9.0/10
- 2026-03-16 | Exclusive: OpenAI courts private equity to join enterprise AI venture, sources say | 影响力 9.0/10
- 2026-03-17 | Baidu joins China's OpenClaw frenzy with new AI agents | 影响力 8.8/10
- 2026-04-01 | AgentSocialBench: Evaluating Privacy Risks in Human-Centered Agentic Social Networks | 影响力 8.8/10
- 2026-04-01 | LLM Agents as Social Scientists: A Human-AI Collaborative Platform for Social Science Automation | 影响力 8.8/10
- 2026-04-09 | Human-AI Collaboration Reconfigures Group Regulation from Socially Shared to Hybrid Co-Regulation | 影响力 8.8/10
- 2026-04-10 | AI-Induced Human Responsibility (AIHR) in AI-Human teams | 影响力 8.9/10
- 2026-04-11 | Building Regulation Capacity in Human-AI Collaborative Learning: A Human-Centred GenAI System | 影响力 8.8/10
- 2026-04-14 | AI agents replicate human social dynamics in days | 影响力 9.1/10
- 2026-04-15 | Cadence, Nvidia working together on developing AI for robotics | 影响力 8.8/10
- 2026-04-16 | Governing Reflective Human-AI Collaboration: A Framework for Epistemic Scaffolding and Traceable Reasoning | 影响力 9.1/10
- 2026-04-16 | From Procedural Skills to Strategy Genes: Towards Experience-Driven Test-Time Evolution | 影响力 8.9/10
- 2026-04-17 | Imperfectly Cooperative Human-AI Interactions: Comparing the Impacts of Human and AI Attributes in Simulated and User Studies | 影响力 8.9/10
- 2026-04-17 | China's EvoMap Changes AI Agent's License After Accusing Nous Research of Copying Code | 影响力 8.9/10
- 2026-04-18 | Intelligent Drill-Down: Large Language Model-Driven Drill-Down Technique for Human-AI Collaborative Visual Exploration | 影响力 8.6/10
- 2026-04-18 | Graph-of-Agents: A Graph-based Framework for Multi-Agent LLM Collaboration | 影响力 8.9/10
- 2026-04-18 | Social and emotional learning in artificial agents | 影响力 8.7/10
- 2026-04-20 | When AI Agents Disagree Like Humans: Reasoning Trace Analysis for Human-AI Collaborative Moderation | 影响力 9.0/10
- 2026-04-21 | Scaffolding Human-AI Collaboration: A Field Experiment on Behavioral Protocols and Cognitive Reframing | 影响力 8.8/10
- 2026-04-21 | Human-Symbiotic Agent Network for Cross-User Autonomous Cooperation | 影响力 9.2/10
- 2026-04-21 | AI research lab NeoCognition lands $40M seed to build agents that learn like humans | 影响力 8.6/10
- 2026-04-21 | No humans allowed: scientific AI agents get their own social network | 影响力 8.9/10
- 2026-04-21 | Volkswagen to equip Chinese cars with AI agents, in bid to catch up in tech | 影响力 8.7/10
- 2026-04-22 | Aligning Human-AI-Interaction Trust for Mental Health Support: Survey and Position for Multi-Stakeholders | 影响力 8.7/10
- 2026-04-22 | Cooperative Profiles Predict Multi-Agent LLM Team Performance in AI for Science Workflows | 影响力 9.1/10
- 2026-04-22 | Google puts AI agents at heart of its enterprise money-making push | 影响力 8.9/10
- 2026-04-23 | OpenAI unveils Workspace Agents, a successor to custom GPTs for enterprises that can plug directly into Slack, Salesforce and more | 影响力 8.9/10
- 2026-04-23 | Towards a societal AI alignment benchmark for evaluating human-machine value convergence | 影响力 8.8/10
- 2026-04-23 | The Platform Is Mostly Not a Platform: Token Economies and Agent Discourse on Moltbook | 影响力 9.0/10
- 2026-04-24 | DeepSeek unveils new AI model tailored for Huawei chips as China pushes for tech autonomy | 影响力 9.0/10
- 2026-04-24 | When AI Agents Learn from Each Other: Insights from Emergent AI Agent Communities on OpenClaw for Human-AI Partnership in Education | 影响力 8.8/10
- 2026-04-27 | China orders Meta to unwind $2 billion purchase of AI startup Manus | 影响力 9.2/10
- 2026-04-28 | OpenAI's latest AI models, Codex now available on Amazon Bedrock | 影响力 8.8/10
- 2026-04-28 | AI agent behavioral science | 影响力 9.0/10
- 2026-04-29 | The Synthetic Social Graph: Emergent Behavior in AI Agent Communities | 影响力 9.3/10
- 2026-04-29 | What we learned about humans and agents collaborating in the intelligent enterprise | 影响力 8.5/10
- 2026-04-29 | Addressing the Reality Gap: A Three-Tension Framework for Agentic AI Adoption | 影响力 8.7/10
- 2026-04-30 | Catalyst discovery through AI agent collaboration | 影响力 8.6/10
- 2026-05-01 | Call your AI agent | 影响力 8.9/10
- 2026-05-01 | On the Role of Artificial Intelligence in Human-Machine Symbiosis | 影响力 9.0/10
- 2026-05-05 | AIs and Humans with Agency | 影响力 9.1/10
- 2026-05-05 | Collective intelligence framework shows how human-AI teams may make better decisions | 影响力 8.8/10
- 2026-05-05 | Stayin’ Aligned Over Time: Towards Longitudinal Human-LLM Alignment via Contextual Reflection and Privacy-Preserving Behavioral Data | 影响力 9.0/10
- 2026-05-05 | A Workflow-Oriented Framework for Asynchronous Human-AI Collaboration in Hybrid and Compute-Intensive HPC Environments | 影响力 8.7/10
- 2026-05-05 | From Intent to Execution: Composing Agentic Workflows with Agent Recommendation | 影响力 8.6/10
- 2026-05-06 | LongSeeker: Elastic Context Orchestration for Long-Horizon Search Agents | 影响力 8.8/10
- 2026-05-06 | OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents | 影响力 8.7/10
- 2026-05-06 | Human-AI Co-Mentorship in Project-Based Learning: A Case Study in Financial Forecasting | 影响力 8.4/10
- 2026-05-07 | Sustaining Cooperation in Populations Guided by AI: A Folk Theorem for LLMs | 影响力 9.1/10
- 2026-05-07 | SkillOS: Learning Skill Curation for Self-Evolving Agents | 影响力 9.0/10
- 2026-05-07 | Recursive Agent Optimization | 影响力 9.0/10
- 2026-05-07 | STALE: Can LLM Agents Know When Their Memories Are No Longer Valid? | 影响力 8.9/10
- 2026-05-07 | PrefixGuard: From LLM-Agent Traces to Online Failure-Warning Monitors | 影响力 8.8/10
- 2026-05-07 | AI Co-Mathematician: Accelerating Mathematicians with Agentic AI | 影响力 9.0/10
- 2026-05-07 | Cited but Not Verified: Parsing and Evaluating Source Attribution in LLM Deep Research Agents | 影响力 8.8/10
- 2026-05-07 | MASPO: Joint Prompt Optimization for LLM-based Multi-Agent Systems | 影响力 8.8/10
- 2026-05-07 | Ex Ante Evaluation of AI-Induced Idea Diversity Collapse | 影响力 8.9/10
- 2026-05-07 | Human-AI Co-Evolution and Epistemic Collapse: A Dynamical Systems Perspective | 影响力 9.1/10
- 2026-05-07 | Prediction and Empowerment: A Theory of Agency through Bridge Interfaces | 影响力 8.8/10
- 2026-05-07 | Agentic AIs Are the Missing Paradigm for Out-of-Distribution Generalization in Foundation Models | 影响力 8.9/10
- 2026-05-07 | Beyond Task Success: Measuring Workflow Fidelity in LLM-Based Agentic Payment Systems | 影响力 8.7/10
- 2026-05-07 | NeuroAgent: LLM Agents for Multimodal Neuroimaging Analysis and Research | 影响力 8.6/10
- 2026-05-08 | Collaborator or Assistnat? How AI Coding Agents Partition Work Across Pull Request Lifecycles | 影响力 8.9/10
- 2026-05-08 | Ask Early, Ask Late, Ask Right: When Does Clarification Timing Matter for Long-Horizon Agents? | 影响力 8.8/10
- 2026-05-08 | Sycophantic AI makes human interaction feel more effortful and less satisfying over time | 影响力 9.2/10
- 2026-05-08 | What if AI systems weren't chatbots? | 影响力 9.0/10
- 2026-05-12 | LongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced Colleagues | 影响力 9.2/10
- 2026-05-12 | Optimized but Unowned: How AI-Authored Goals Undermine the Motivation They Are Meant to Drive | 影响力 9.1/10
- 2026-05-12 | Predicting Decisions of AI Agents from Limited Interaction through Text-Tabular Modeling | 影响力 9.0/10
- 2026-05-12 | No Action Without a NOD: A Heterogeneous Multi-Agent Architecture for Reliable Service Agents | 影响力 8.9/10
- 2026-05-12 | PRISM: Pareto-Efficient Retrieval over Intent-Aware Structured Memory for Long-Horizon Agents | 影响力 8.9/10
- 2026-05-12 | ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents | 影响力 8.8/10
- 2026-05-12 | Executable Agentic Memory for GUI Agent | 影响力 8.8/10
- 2026-05-12 | Multi-Stream LLMs: Unblocking Language Models with Parallel Streams of Thoughts, Inputs and Outputs | 影响力 8.7/10
- 2026-05-13 | Good Agentic Friends Do Not Just Give Verbal Advice: They Can Update Your Weights | 影响力 9.3/10
- 2026-05-13 | SkillOps: Managing LLM Agent Skill Libraries as Self-Maintaining Software Ecosystems | 影响力 9.2/10
- 2026-05-13 | Sleeper Channels and Provenance Gates: Persistent Prompt Injection in Always-on Autonomous AI Agents | 影响力 9.2/10
- 2026-05-13 | How to Interpret Agent Behavior | 影响力 9.1/10
- 2026-05-13 | ProjGuard: Safety Monitoring for Computer-Use Agents via Low-Dimensional Projections | 影响力 9.0/10
- 2026-05-13 | Cognifold: Always-On Proactive Memory via Cognitive Folding | 影响力 9.0/10
- 2026-05-13 | TRIAGE: Evaluating Prospective Metacognitive Control in LLMs under Resource Constraints | 影响力 8.9/10
- 2026-05-13 | CANTANTE: Optimizing Agentic Systems via Contrastive Credit Attribution | 影响力 8.9/10
- 2026-05-13 | ScioMind: Cognitively Grounded Multi-Agent Social Simulation with Anchoring-Based Belief Dynamics and Dynamic Profiles | 影响力 8.8/10
- 2026-05-13 | MAP: A Map-then-Act Paradigm for Long-Horizon Interactive Agent Reasoning | 影响力 8.8/10
- 2026-05-14 | FutureSim: Replaying World Events to Evaluate Adaptive Agents | 影响力 9.0/10
- 2026-05-14 | Is Grep All You Need? How Agent Harnesses Reshape Agentic Search | 影响力 8.8/10
- 2026-05-14 | APWA: A Distributed Architecture for Parallelizable Agentic Workflows | 影响力 8.8/10
- 2026-05-14 | MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory | 影响力 8.7/10
- 2026-05-14 | Why Neighborhoods Matter: Traversal Context and Provenance in Agentic GraphRAG | 影响力 8.7/10
- 2026-05-14 | After the Interface: Relocating Human Agency in the Age of Conversational AI | 影响力 9.1/10
- 2026-05-14 | WARD: Adversarially Robust Defense of Web Agents Against Prompt Injections | 影响力 9.0/10
- 2026-05-14 | Toward Securing AI Agents Like Operating Systems | 影响力 9.3/10
- 2026-05-14 | Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems | 影响力 9.0/10
- 2026-05-14 | Holistic Evaluation and Failure Diagnosis of AI Agents | 影响力 8.9/10
- 2026-05-14 | Do Coding Agents Understand Least-Privilege Authorization? | 影响力 8.9/10
- 2026-05-14 | Agentic AI and Human-in-the-Loop Interventions: Field Experimental Evidence from Alibaba's Customer Service Operations | 影响力 9.1/10
- 2026-05-14 | Beyond AI as Assistants: Toward Autonomous Discovery in Cosmology | 影响力 9.2/10
- 2026-05-14 | Known By Their Actions: Fingerprinting LLM Browser Agents via UI Traces | 影响力 8.8/10
- 2026-05-14 | MediaClaw: Multimodal Intelligent-Agent Platform Technical Report | 影响力 8.8/10
- 2026-05-14 | Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining | 影响力 8.6/10
- 2026-05-14 | AI Knows When It's Being Watched: Functional Strategic Action and Contextual Register Modulation in Large Language Models | 影响力 9.1/10
- 2026-05-14 | Auditing Agent Harness Safety | 影响力 9.2/10
- 2026-05-14 | Making OpenAPI Documentation Agent-Ready: Detecting Documentation and REST Smells with a Multi-Agent LLM System | 影响力 8.7/10
- 2026-05-14 | Exploiting LLM Agent Supply Chains via Payload-less Skills | 影响力 9.2/10
- 2026-05-14 | Position: Behavioural Assurance Cannot Verify the Safety Claims Governance Now Demands | 影响力 9.0/10
- 2026-05-18 | FORGE: Self-Evolving Agent Memory With No Weight Updates via Population Broadcast | 影响力 9.3/10
- 2026-05-18 | Verifiable Agentic Infrastructure: Proof-Derived Authorization for Sovereign AI Systems | 影响力 9.3/10
- 2026-05-18 | Argus: Evidence Assembly for Scalable Deep Research Agents | 影响力 9.2/10
- 2026-05-18 | paper.json: A Coordination Convention for LLM-Agent-Actionable Papers | 影响力 9.0/10
- 2026-05-18 | SaaS-Bench: Can Computer-Use Agents Leverage Real-World SaaS to Solve Professional Workflows? | 影响力 9.0/10
- 2026-05-18 | Belief Engine: Configurable and Inspectable Stance Dynamics in Multi-Agent LLM Deliberation | 影响力 8.9/10
- 2026-05-18 | SkillSmith: Compiling Agent Skills into Boundary-Guided Runtime Interfaces | 影响力 8.9/10
- 2026-05-18 | RecMem: Recurrence-based Memory Consolidation for Efficient and Effective Long-Running LLM Agents | 影响力 8.8/10
- 2026-05-19 | Agentic AI Ecosystems in Higher Education: A Perspective on AI Agents and Multi-Agent Systems | 影响力 8.8/10
- 2026-05-19 | With Gemini 3.5 Flash, Google bets its next AI wave on agents, not chatbots | 影响力 9.0/10
- 2026-05-19 | How to use Google’s new AI agents to go beyond your standard searches | 影响力 8.8/10
- 2026-05-20 | Code as Agent Harness | 影响力 8.8/10
- 2026-05-20 | OpenClaw Is the Hot New AI Agent, But Is It Safe to Use? | 影响力 8.6/10
- 2026-05-21 | Google is pitching an AI agent ecosystem to consumers who may not buy it | 影响力 8.7/10
- 2026-05-21 | Agent Security is a Systems Problem | 影响力 9.4/10
- 2026-05-21 | Governance by Construction for Generalist Agents | 影响力 9.4/10
- 2026-05-21 | Heartbeat-Bound Hierarchical Credentials: Cryptographic Revocation for AI Agent Swarms | 影响力 9.3/10
- 2026-05-21 | MemGym: a Long-Horizon Memory Environment for LLM Agents | 影响力 9.2/10
- 2026-05-21 | Terminal-World: Scaling Terminal-Agent Environments via Agent Skills | 影响力 9.1/10
- 2026-05-21 | An Application-Layer Multi-Modal Covert-Channel Reference Monitor for LLM Agent Egress | 影响力 9.1/10
- 2026-05-21 | What Twelve LLM Agent Benchmark Papers Disclose About Themselves: A Pilot Audit and an Open Scoring Schema | 影响力 9.0/10
- 2026-05-21 | APEX: Autonomous Policy Exploration for Self-Evolving LLM Agents | 影响力 9.0/10
- 2026-05-22 | Multi-agent AI systems outperform human teams in creativity | 影响力 9.4/10
- 2026-05-22 | MetaCogAgent: A Metacognitive Multi-Agent LLM Framework with Self-Aware Task Delegation | 影响力 9.2/10
- 2026-05-22 | Code as Agent Harness: Toward Executable, Verifiable, and Stateful Agent Systems | 影响力 9.1/10
- 2026-05-22 | OpenClaw: The AI Agent Security Crisis Unfolding Right Now | 影响力 8.8/10
- 2026-05-23 | EvoMap/evolver: GEP-powered self-evolving engine for AI agents | 影响力 9.0/10
- 2026-05-23 | moltbook - the front page of the agent internet | 影响力 8.6/10
- 2026-05-23 | MOSS: Self-Evolution through Source-Level Rewriting in Autonomous Agent Systems | 影响力 9.4/10
- 2026-05-23 | LCGuard: Latent Communication Guard for Safe KV Sharing in Multi-Agent Systems | 影响力 9.2/10
- 2026-05-23 | DeltaBox: Scaling Stateful AI Agents with Millisecond-Level Sandbox Checkpoint/Rollback | 影响力 9.1/10
- 2026-05-23 | Remember to be Curious: Episodic Context and Persistent Worlds for 3D Exploration | 影响力 8.8/10
- 2026-05-23 | AwareVLN: Reasoning with Self-awareness for Vision-Language Navigation | 影响力 8.7/10
- 2026-05-24 | Self-Evolving Multi-Agent Systems via Decentralized Memory | 影响力 9.3/10
- 2026-05-24 | Claw AI Lab: An Autonomous Multi-Agent Research Team | 影响力 9.2/10
- 2026-05-24 | Contractual Skills: A GovernSpec Design Framework for Enterprise AI Agents | 影响力 9.1/10
- 2026-05-24 | Measuring Security Without Fooling Ourselves: Why Benchmarking Agents Is Hard | 影响力 9.1/10
- 2026-05-24 | The Human-AI Delegation Dilemma: Individual Strategies, Collective Equilibria and Sociotechnical Lock-in | 影响力 9.0/10
- 2026-05-25 | Automated Benchmark Auditing for AI Agents and Large Language Models | 影响力 9.1/10
- 2026-05-25 | Anticipate and Learn: Unleashing Idle-Time Compute in Proactive Agents | 影响力 9.0/10
- 2026-05-25 | Multi-Agent Systems are Mixtures of Experts: Who Becomes an Influencer? | 影响力 9.2/10
- 2026-05-25 | The Timing Dependencies of Trust: Speed, Accuracy, and cBCI Neuro-Decoupling in Human-AI Teams | 影响力 9.0/10
- 2026-05-25 | Behind EvoMap: Characterizing a Self-Evolving Agent-to-Agent Collaboration Network | 影响力 9.4/10
- 2026-05-25 | Multi-Agent Coordination Adaptation via Structure-Guided Orchestration | 影响力 9.1/10
- 2026-05-25 | When Agents Control Robots: A Zero Trust Policy Model for Agentic Cyber-Physical Systems | 影响力 9.2/10
- 2026-05-25 | Retrieval as Reasoning: Self-Evolving Agent-Native Retrieval via LLM-Wiki | 影响力 9.1/10
- 2026-05-25 | Security of OpenClaw Agents: Fundamentals, Attacks, and Countermeasures | 影响力 9.3/10
- 2026-05-25 | CODESKILL: Learning Self-Evolving Skills for Coding Agents | 影响力 9.0/10
- 2026-05-26 | Sandlock: Confining AI Agent Code with Unprivileged Linux Primitives | 影响力 9.1/10
- 2026-05-26 | Towards Feedback-to-Plan Decisions for Self-Evolving LLM Agents in CUDA Kernel Generation | 影响力 8.8/10
- 2026-05-26 | Accountable Human-AI Deliberation with LLMs: Scaling Collective Intelligence through Symbiotic Scaffolding | 影响力 9.3/10
- 2026-05-26 | Lessons from Penetration Tests on Large-Scale Agent Systems | 影响力 9.2/10
- 2026-05-26 | Governed Evolution of Agent Runtimes through Executable Operational Cognition | 影响力 9.4/10
- 2026-05-26 | Exploring Agent Interactions in MoltBook through Social Network Analysis | 影响力 9.3/10
- 2026-05-26 | GENESIS: Harnessing AI Agents for Autonomous 6G RAN Synthesis, Research, and Testing | 影响力 9.0/10
- 2026-05-26 | MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation | 影响力 9.3/10
- 2026-05-27 | SwarmHarness: Skill-Based Task Routing via Decentralized Incentive-Aligned AI Agent Networks | 影响力 9.4/10
- 2026-05-27 | AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation | 影响力 9.3/10
- 2026-05-27 | Technical Report: Exploring the Emerging Threats of the Agent Skill Ecosystem | 影响力 9.3/10
- 2026-05-27 | Roles with Rails: Contract-Preserving Role Evolution in Multi-Agent Structured Reasoning | 影响力 9.1/10
- 2026-05-27 | AI, Take the Wheel: What Drives Delegation and Trust in Human-Computer Cooperative Question Answering? | 影响力 9.1/10
- 2026-05-28 | Physics Is All You Need? A Case Study in Physicist-Supervised AI Development of Scientific Software | 影响力 9.3/10
- 2026-05-28 | Locally Coherent, Globally Incoherent: Bounding Compositional Incoherence in Multi-Component LLM Agents | 影响力 9.2/10
- 2026-05-28 | SoundnessBench: Can Your AI Scientist Really Tell Good Research Ideas from Bad Ones? | 影响力 9.3/10
- 2026-05-28 | Gram: Assessing sabotage propensities via automated alignment auditing | 影响力 9.4/10
- 2026-05-28 | EASE Configuration Facilitates A Reproducible Science of LLM Social Simulations | 影响力 9.1/10
- 2026-05-28 | Dissociative Identity: Language Model Agents Lack Grounding for Reputation Mechanisms | 影响力 9.2/10
- 2026-05-28 | Meta-Cognitive Memory Policy Optimization for Long-Horizon LLM Agents | 影响力 9.2/10
- 2026-05-28 | AgentSchool: An LLM-Powered Multi-Agent Simulation for Education | 影响力 9.0/10
- 2026-05-28 | Enhancing Multi-Agent Communication through Attention Steering with Context Relevance | 影响力 9.0/10
- 2026-05-28 | When Cloud Agents Meet Device Agents: Lessons from Hybrid Multi-Agent Systems | 影响力 9.1/10
- 2026-05-28 | HEART-Bench: Do LLM Agents Exhibit Human-like Psychology? | 影响力 9.2/10
- 2026-05-27 | Extending Human Intelligence Through AI | 影响力 9.1/10
- 2026-05-28 | Who Does Your AI Work For? Designing Conversational Agents as Digital Fiduciaries | 影响力 9.3/10
- 2026-05-28 | From Prompts to Context: An Ontology-Driven Framework for Human-Generative AI Collaboration | 影响力 9.1/10
- 2026-05-28 | Discovering Cooperative Pipelines: Autoresearch for Sequential Social Dilemmas | 影响力 9.0/10
- 2026-05-29 | Human–AI interactions reshape the self and our social networks | 影响力 9.4/10
- 2026-05-29 | Asana was battered by the AI age. Now it’s betting its future on humans and agents working together | 影响力 8.8/10
- 2026-06-02 | Human-AI Collaboration: Transitioning From Automation To Augmentation | 影响力 8.4/10
- 2026-06-02 | Deliberative Curation: A Protocol for Multi-Agent Knowledge Bases | 影响力 9.2/10
- 2026-06-02 | AI and the New Future of Work: Spring 2026 CFP | 影响力 8.9/10
- 2026-06-02 | Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories | 影响力 9.0/10
- 2026-06-02 | Agentic Chain-of-Thought Steering for Efficient and Controllable LLM Reasoning | 影响力 8.7/10
- 2026-06-03 | Organizational Control Layer: Governance Infrastructure at the Execution Boundary of LLM Agent Systems | 影响力 9.4/10
- 2026-06-03 | The Digital Apprentice: A Framework for Human-Directed Agentic AI Development | 影响力 9.3/10
- 2026-06-03 | Tree-Based Formalization of Multi-Agent Complementarity in Human-AI Interactions | 影响力 9.3/10
- 2026-06-03 | Autonomous heterogeneous catalyst discovery with a self-evolving multi-agent digital twin | 影响力 8.8/10
- 2026-06-03 | Streaming Communication in Multi-Agent Reasoning | 影响力 9.0/10
- 2026-06-04 | A rich, HTML-native document canvas for human <> AI collaboration | 影响力 8.2/10
- 2026-06-04 | Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? | 影响力 9.2/10
- 2026-06-04 | Beyond Alignment: Value Diversity as a Collective Property in Multicultural Agent Systems | 影响力 9.1/10
- 2026-06-04 | EGTR-Review: Efficient Evidence-Grounded Scientific Peer Review Generation via Multi-Agent Teacher Distillation | 影响力 8.6/10
- 2026-06-04 | CollabSim: A CSCW-Grounded Methodology for Investigating Collaborative Competence of LLM Agents through Controlled Multi-Agent Experiments | 影响力 9.3/10
- 2026-06-04 | Agents' Last Exam | 影响力 9.0/10
- 2026-06-04 | Agentic Software: How AI Agents Are Restructuring the Software Paradigm | 影响力 8.8/10
- 2026-06-05 | Kaya Suites – An AI Native Knowledge Base | 影响力 8.1/10
- 2026-06-05 | Agentopia: Long-Term Life Simulation and Learning in Agent Societies | 影响力 9.4/10
- 2026-06-05 | How AI Agents Reshape Knowledge Work: Autonomy, Efficiency, and Scope | 影响力 9.3/10
- 2026-06-05 | Act As a Real Researcher: A Suite of Benchmarks Evaluating Frontier LLMs and Agentic Harnesses in Research Lifecycle | 影响力 9.2/10
- 2026-06-05 | Agentic Very Much! Adoption of Coding Agent in New GitHub Projects | 影响力 9.0/10
- 2026-06-05 | Modelling Opinion Dynamics at Scale with Deep MARL | 影响力 8.8/10
- 2026-06-05 | OPENPATH: A Supervisor--Specialist Agent System for Personalized, Accessible, and Multi-stop Urban Trip Planning | 影响力 8.7/10
- 2026-06-08 | Collaborative Human-Agent Protocol (CHAP) | 影响力 9.4/10
- 2026-06-08 | SIGA: Self-Evolving Coding-Agent Adapters for Scientific Simulation | 影响力 9.2/10
- 2026-06-08 | SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research | 影响力 9.1/10
- 2026-06-08 | Multi-Turn Evaluation of Deep Research Agents Under Process-Level Feedback | 影响力 9.0/10
- 2026-06-08 | OmniGameArena: A Unified UE5 Benchmark for VLM Game Agents with Improvement Dynamics | 影响力 8.8/10
- 2026-06-09 | Human-AI Teaming Through the Lens of Calibration | 影响力 9.4/10
- 2026-06-09 | EEVEE: Towards Test-time Prompt Learning in the Real World for Self-Improving Agents | 影响力 9.3/10
- 2026-06-09 | Role-Agent: Bootstrapping LLM Agents via Dual-Role Evolution | 影响力 9.2/10
- 2026-06-09 | Moonshine: An Autonomous Mathematical Research Agent Centered on Conjecture Generation | 影响力 9.1/10
- 2026-06-09 | ABC-Bench: An Agentic Bio-Capabilities Benchmark for Biosecurity | 影响力 9.0/10
- 2026-06-09 | Harnessing the Collective Intelligence of AI Agents in the Wild for New Discoveries | 影响力 9.2/10
- 2026-06-10 | Nonslop: A Gamified Experiment in Human-AI Collaborative Writing | 影响力 9.2/10
- 2026-06-10 | MODF-SIR: A Multi-agent Omni-modal Distilled Framework for Social Intelligence Reasoning | 影响力 9.2/10
- 2026-06-10 | Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application | 影响力 9.1/10
- 2026-06-10 | Human-Enhanced Loop Modeling (HELM): Agent-Based Finite Element Modeling of Concrete Bridge Barriers | 影响力 9.1/10
- 2026-06-10 | Embodied-BenchClaw: An Autonomous Multi-Agent System for Embodied Spatial Intelligence Benchmark Construction | 影响力 9.1/10
- 2026-06-10 | CCKS: Consensus-based Communication and Knowledge Sharing | 影响力 8.9/10
- 2026-06-11 | EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments | 影响力 9.4/10
- 2026-06-11 | EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery | 影响力 9.3/10
- 2026-06-11 | Agents-K1: Towards Agent-native Knowledge Orchestration | 影响力 9.2/10
- 2026-06-11 | AgentBeats: Agentifying Agent Assessment for Openness, Standardization, and Reproducibility | 影响力 9.1/10
- 2026-06-11 | Recursive Agent Harnesses | 影响力 9.0/10
- 2026-06-11 | Exploring Systems-Thinking Approaches to Loss of Control Risk | 影响力 9.0/10
- 2026-06-11 | InterleaveThinker: Reinforcing Agentic Interleaved Generation | 影响力 9.1/10
- 2026-06-11 | HyperTool: Beyond Step-Wise Tool Calls for Tool-Augmented Agents | 影响力 9.0/10
- 2026-06-11 | Reward Modeling for Multi-Agent Orchestration | 影响力 8.9/10
- 2026-06-11 | See What I See, Know What I Think: Dense Latent Communication Across Heterogeneous Agents | 影响力 8.9/10
- 2026-06-11 | SkillCAT: Contrastive Assessment and Topology-Aware Skill Self-Evolution for LLM Agents | 影响力 8.8/10
- 2026-06-11 | MemRefine: LLM-Guided Compression for Long-Term Agent Memory | 影响力 8.8/10